AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB) spec sheet

What your AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB) can run

We check your graphics card or Mac against every model in the catalog. Your browser reports the GPU model but not its memory, so confirm the exact version below.

Your GPU or Mac

Unified memory: 32.0 GB
Usable for models: 24.0 GB
Memory bandwidth: 90 GB/s
FP16 compute: 25.4 TFLOPS

409 / 536 LLMs run Best: Gemma 4 26B-A4B (S) 46 / 47 Image models run Best: FLUX.2 [klein] 9B (S) 25 / 34 Video models run Best: LTX-Video 2B (A)

Open in Model Finder Best LLMs by task Compare with another GPU

LLMs on your AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 15.0/15	Gemma 4 26B-A4BGoogle · 26B (3.8B active)	`Q4_K_M`	18.7 GB	12.5 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)	`Q3_K_M`	20.3 GB	20.4 tok/s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 9.4/15, Memory use 15.0/15	GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)	`Q4_K_M`	22.0 GB	15.8 tok/s	Tight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 35.2/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)	`Q3_K_M`	20.3 GB	20.4 tok/s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 9.4/15, Memory use 15.0/15	Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)	`Q4_K_M`	23.8 GB	15.8 tok/s	Tight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Qwen3.8 27BAlibaba · 28B	`Q4_K_M`	20.0 GB	3.4 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 34.0/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)	`Q3_K_M`	20.3 GB	20.4 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Qwen3.6 27BAlibaba · 28B	`Q4_K_M`	20.0 GB	3.4 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)	`Q3_K_M`	20.3 GB	20.4 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)	`Q3_K_M`	20.3 GB	20.4 tok/s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Qwen3.5 27BAlibaba · 28B	`Q4_K_M`	20.0 GB	3.4 tok/s	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Agents-A1 35B-A3BInternScience · 35B (3.0B active)	`Q3_K_M`	19.9 GB	20.4 tok/s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	TMax 27BAi2 · 27B	`Q4_K_M`	19.7 GB	3.5 tok/s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 9.4/15, Memory use 15.0/15	North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)	`Q4_K_M`	21.4 GB	15.8 tok/s	Tight fit
82 ptsGreat (A) · 82 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Fara 1.5 27BMicrosoft · 27B	`Q4_K_M`	19.7 GB	3.5 tok/s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 38.9/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	Gemma 4 31BGoogle · 31B	`Q4_K_M`	23.2 GB	3.0 tok/s	Tight fit
81 ptsGreat (A) · 81 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 8.7/15, Memory use 15.0/15	Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)	`Q4_K_M`	21.8 GB	13.5 tok/s	Tight fit
81 ptsGreat (A) · 81 of 100 points: Model quality 31.0/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15	Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)	`Q3_K_M`	20.2 GB	20.4 tok/s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 15.0/15	DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)	`Q4_K_M`	18.7 GB	11.8 tok/s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)	`Q4_K_M`	21.9 GB	14.4 tok/s	Tight fit
81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)	`Q4_K_M`	21.9 GB	14.4 tok/s	Tight fit
81 ptsGreat (A) · 81 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	UI-Mate 27BTencent · 27B	`Q4_K_M`	19.7 GB	3.5 tok/s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)	`Q4_K_M`	21.9 GB	14.4 tok/s	Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 8.7/15, Memory use 15.0/15	Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)	`Q4_K_M`	21.8 GB	13.5 tok/s	Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)	`Q4_K_M`	22.3 GB	14.4 tok/s	Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 12.5/15	Gemma 4 12BGoogle · 12B	`Q6_K`	13.0 GB	5.5 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3 30B-A3BAlibaba · 31B (3.3B active)	`Q4_K_M`	21.9 GB	14.4 tok/s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 9.0/15, Memory use 15.0/15	Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)	`Q4_K_M`	22.3 GB	14.4 tok/s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 14.1/15	gpt-oss 20BOpenAI · 21B (3.6B active)	`MXFP4`	14.7 GB	14.1 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 10.5/15, Memory use 15.0/15	Sarvam 30BSarvam AI · 32B (2.4B active)	`Q4_K_M`	22.3 GB	19.7 tok/s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 15.0/15	ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)	`Q4_K_M`	16.3 GB	15.8 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 9.4/15, Memory use 15.0/15	Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)	`Q4_K_M`	21.8 GB	15.8 tok/s	Tight fit
77 ptsGreat (A) · 77 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 15.0/15	Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)	`Q4_K_M`	18.6 GB	15.8 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Devstral Small 2 (24B)Mistral AI · 24B	`Q4_K_M`	18.5 GB	3.9 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Phi-4 Reasoning Plus (14B)Microsoft · 15B	`Q6_K`	16.2 GB	4.5 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Apriel 1.5 15B ThinkerServiceNow · 15B	`Q6_K`	16.3 GB	4.4 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 15.0/15	ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)	`Q4_K_M`	16.4 GB	15.8 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Phi-4 Reasoning (14B)Microsoft · 15B	`Q6_K`	16.2 GB	4.5 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 4.9/15, Memory use 15.0/15	Phi-4 Reasoning Vision 15BMicrosoft · 15B	`Q6_K`	16.6 GB	4.3 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 10.3/15	Ornith 1.5 9BDeepReinforce · 9.7B	`Q6_K`	10.7 GB	6.8 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 4.3/15, Memory use 15.0/15	Granite 4.2 30BIBM · 29B	`Q4_K_M`	22.5 GB	3.2 tok/s	Tight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 10.2/15, Memory use 15.0/15	Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)	`Q3_K_M`	20.6 GB	18.6 tok/s	Tight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	Olmo 3.1 32B ThinkAi2 · 32B	`Q4_K_M`	22.9 GB	2.9 tok/s	Tight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Magistral Small 1.2 (24B)Mistral AI · 24B	`Q4_K_M`	18.5 GB	3.9 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 31.0/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	EXAONE 4.5 33BLG AI Research · 34B	`Q3_K_M`	20.1 GB	3.6 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 10.3/15	Qwen3.5 9BAlibaba · 9.7B	`Q6_K`	10.7 GB	6.8 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 30.3/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Qwen3 14BAlibaba · 15B	`Q6_K`	16.0 GB	4.4 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Gemma 3 27B ITGoogle · 27B	`Q4_K_M`	20.0 GB	3.5 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 33.4/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 10.3/15	Ornith 1.0 9BDeepReinforce · 9.7B	`Q6_K`	10.7 GB	6.8 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15	LFM2 24B-A2BLiquid AI · 24B (2.3B active)	`Q4_K_M`	17.2 GB	20.6 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 4.0/15, Memory use 15.0/15	GLM-4 32B 0414Zhipu AI · 33B	`Q4_K_M`	22.9 GB	2.9 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 4.0/15, Memory use 15.0/15	GLM-Z1 32B (0414)Zhipu AI · 33B	`Q4_K_M`	22.9 GB	2.9 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Devstral Small 1.1 (24B)Mistral AI · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Magistral Small 2507Mistral AI · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	AceReason Nemotron 14BNVIDIA · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Hermes 4 14BNous Research · 15B	`Q6_K`	16.0 GB	4.4 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	OpenReasoning Nemotron 14BNVIDIA · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Qwen2.5 Coder 14B InstructAlibaba · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 23.3/45, Memory fit 24.0/25, Speed 12.1/15, Memory use 15.0/15	Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)	`Q2_K`	22.2 GB	25.9 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Apriel Nemotron 15B ThinkerServiceNow · 15B	`Q6_K`	16.5 GB	4.4 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	MedGemma 27B Text ITGoogle · 27B	`Q4_K_M`	19.8 GB	3.5 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 5.1/15, Memory use 14.7/15	Ministral 3 14B ReasoningMistral AI · 14B	`Q6_K`	15.3 GB	4.7 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 9.7/15	TMax 9BAi2 · 9.0B	`Q6_K`	10.1 GB	7.3 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 4.3/15, Memory use 15.0/15	Granite 4.1 30BIBM · 29B	`Q4_K_M`	22.3 GB	3.3 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	EXAONE 4.0 32BLG AI Research · 32B	`Q4_K_M`	22.8 GB	3.0 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	Olmo 3.1 32B InstructAi2 · 32B	`Q4_K_M`	22.9 GB	2.9 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Magistral Small 2506Mistral AI · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Mistral Small 3.2 24BMistral AI · 24B	`Q4_K_M`	18.5 GB	3.9 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 30.2/45, Memory fit 24.0/25, Speed 4.4/15, Memory use 15.0/15	Seed-OSS 36B InstructByteDance · 36B	`Q3_K_M`	22.4 GB	3.4 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Phi-4 (14B)Microsoft · 15B	`Q6_K`	16.3 GB	4.5 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	DeepCoder 14B PreviewAgentica · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 4.9/15, Memory use 15.0/15	InternVL3 14BShanghai AI Lab · 15B	`Q6_K`	16.5 GB	4.3 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	Reka Flash 3.1 (21B)Reka AI · 21B	`Q5_K_M`	18.5 GB	3.7 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 5.1/15, Memory use 14.7/15	Ministral 3 14BMistral AI · 14B	`Q6_K`	15.3 GB	4.7 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 12.3/15	Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)	`Q4_K_M`	12.8 GB	33.8 tok/s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 4.4/15, Memory use 15.0/15	Hermes 4.3 36BNous Research · 36B	`Q3_K_M`	22.4 GB	3.4 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	QwQ 32BAlibaba · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 4.5/15, Memory use 15.0/15	Qwen3-VL 32B InstructAlibaba · 33B	`Q3_K_M`	21.0 GB	3.7 tok/s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Devstral Small 2505Mistral AI · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Mistral Small 3.1 24BMistral AI · 24B	`Q4_K_M`	18.5 GB	3.9 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Qwen2.5 14B InstructAlibaba · 15B	`Q6_K`	16.2 GB	4.5 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	DeepSeek R1 Distill Qwen 14BDeepSeek · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	JanusCoder 14BShanghai AI Lab · 15B	`Q6_K`	16.0 GB	4.4 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	EXAONE Deep 32BLG AI Research · 32B	`Q3_K_M`	20.3 GB	3.8 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 10.1/15	UI-Mate 9BTencent · 9.4B	`Q6_K`	10.5 GB	7.0 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 10.1/15	UI-Venus 2 9BAnt Group (inclusionAI) · 9.4B	`Q6_K`	10.5 GB	7.0 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 12.3/15	Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)	`Q4_K_M`	12.8 GB	15.8 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	OpenReasoning Nemotron 32BNVIDIA · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Skywork OR1 32BSkywork · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Qwen3 32BAlibaba · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 7.3/15	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)	`Q4_K_M`	7.6 GB	36.4 tok/s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Mistral Small 3 24B (2501)Mistral AI · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 4.2/15, Memory use 15.0/15	InternVL3.5 38BShanghai AI Lab · 38B	`Q3_K_M`	23.5 GB	3.2 tok/s	Tight fit
71 ptsGood (B) · 71 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Qwen2.5 14B Instruct 1MAlibaba · 15B	`Q6_K`	16.2 GB	4.4 tok/s	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Codestral 22BMistral AI · 22B	`Q5_K_M`	20.2 GB	3.5 tok/s	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Dolphin Mistral 24B Venice EditionCognitive Computations · 24B	`Q4_K_M`	18.5 GB	3.9 tok/s	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15	Voxtral Small 24BMistral AI · 24B	`Q4_K_M`	18.7 GB	3.9 tok/s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 5.4/15, Memory use 15.0/15	Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)	`Q4_K_M`	22.3 GB	5.3 tok/s	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	DeepSeek R1 Distill Qwen 32BDeepSeek · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.9/15	Granite 4.2 8BIBM · 8.8B	`Q4_K_M`	9.2 GB	10.8 tok/s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	Solar Pro Preview 22BUpstage · 22B	`Q5_K_M`	19.6 GB	3.5 tok/s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 15.0/15	Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24B	`Q4_K_M`	18.2 GB	4.0 tok/s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 27.1/45, Memory fit 24.0/25, Speed 4.0/15, Memory use 15.0/15	Gemma 2 27B ITGoogle · 27B	`Q5_K_M`	23.6 GB	2.9 tok/s	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Baichuan M2 32BBaichuan · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	OpenHands LM 32BAll Hands AI · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Qwen2.5 32B InstructAlibaba · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
69 ptsGood (B) · 69 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 4.2/15, Memory use 15.0/15	InternVL3 38BShanghai AI Lab · 38B	`Q3_K_M`	23.5 GB	3.2 tok/s	Tight fit
69 ptsGood (B) · 69 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 11.9/15	DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)	`Q4_K_M`	12.4 GB	19.7 tok/s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	Command R (08-2024) 32BCohere · 32B	`Q4_K_M`	23.6 GB	2.9 tok/s	Tight fit
69 ptsGood (B) · 69 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 7.2/15	Gemma 4 E4BGoogle · 8.0B	`Q4_K_M`	7.5 GB	11.8 tok/s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 4.5/15, Memory use 15.0/15	Qwen2.5-VL 32B InstructAlibaba · 33B	`Q3_K_M`	21.1 GB	3.7 tok/s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 25.3/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Qwen2.5 Coder 32B InstructAlibaba · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 24.2/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	Falcon-H1 34B InstructTII · 34B	`Q3_K_M`	20.2 GB	3.6 tok/s	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	OLMo 2 32B InstructAi2 · 32B	`Q4_K_M`	23.3 GB	2.9 tok/s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 4.1/15, Memory use 15.0/15	Aya Expanse 32BCohere · 32B	`Q4_K_M`	23.6 GB	2.9 tok/s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 24.9/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	QwQ 32B PreviewAlibaba · 33B	`Q3_K_M`	20.7 GB	3.7 tok/s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 12.3/15	Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active)	`Q4_K_M`	12.8 GB	15.8 tok/s	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 13.3/15, Memory use 7.5/15	LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)	`Q4_K_M`	7.8 GB	31.6 tok/s	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.7/15	Qwen3-VL 8B InstructAlibaba · 8.8B	`Q4_K_M`	9.1 GB	10.8 tok/s	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15	Mistral Small 22B (2409)Mistral AI · 22B	`Q5_K_M`	20.2 GB	3.5 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 8.6/15	InternVL3.5 8BShanghai AI Lab · 8.5B	`Q4_K_M`	8.9 GB	11.1 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.4/15	DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2B	`Q4_K_M`	8.7 GB	11.6 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 5.4/15	Qwen3.5 4BAlibaba · 4.7B	`Q4_K_M`	5.6 GB	20.3 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 10.2/15	Gemma 3 12B ITGoogle · 12B	`Q4_K_M`	10.6 GB	7.8 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 5.2/15	TMax 4BAi2 · 4.2B	`Q4_K_M`	5.4 GB	22.5 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.9/15	Granite 4.1 8BIBM · 8.8B	`Q4_K_M`	9.2 GB	10.8 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	Aya Vision 32BCohere · 33B	`Q3_K_M`	20.1 GB	3.7 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 5.5/15	Gemma 4 E2BGoogle · 5.1B	`Q4_K_M`	5.7 GB	18.5 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.7/15	MiniCPM-V 4.5 8BOpenBMB · 8.7B	`Q4_K_M`	9.0 GB	10.9 tok/s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.4/15	Qwen3 8BAlibaba · 8.2B	`Q4_K_M`	8.7 GB	11.6 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 5.3/15	Agents-A1 4BInternScience · 4.5B	`Q4_K_M`	5.6 GB	20.9 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.2/15, Memory use 8.8/15	GLM-4.1V 9B ThinkingZhipu AI · 10B	`Q4_K_M`	9.1 GB	9.2 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15	InternLM2.5 20B ChatShanghai AI Lab · 20B	`Q4_K_M`	16.2 GB	4.8 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 5.9/15	Qwen3 4B Thinking 2507Alibaba · 4.0B	`Q4_K_M`	6.2 GB	23.6 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 7.2/15	Granite 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)	`Q5_K_M`	7.5 GB	39.1 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 8.5/15	MiMo-VL 7B RLXiaomi · 8.3B	`Q4_K_M`	8.8 GB	11.4 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 7.8/15	Nemotron Nano 9B v2NVIDIA · 8.9B	`Q4_K_M`	8.1 GB	10.7 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 8.3/15	Seed-Coder 8B ReasoningByteDance · 8.3B	`Q4_K_M`	8.6 GB	11.5 tok/s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 12.0/15	Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)	`Q4_K_M`	12.5 GB	15.8 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 5.3/15	Fara 1.5 4BMicrosoft · 4.5B	`Q4_K_M`	5.6 GB	20.9 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 6.4/15	Mage-VL 4.7BMicrosoft · 4.7B	`Q4_K_M`	6.6 GB	20.0 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 17.6/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 15.0/15	Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)	`Q2_K`	20.3 GB	11.8 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 8.3/15	GLM-Z1 9B (0414)Zhipu AI · 9.4B	`Q4_K_M`	8.6 GB	10.1 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 5.9/15	Qwen3 4B Instruct 2507Alibaba · 4.0B	`Q4_K_M`	6.2 GB	23.6 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 8.8/15	Ministral 3 8BMistral AI · 8.9B	`Q4_K_M`	9.1 GB	10.6 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 8.2/15	MiMo 7B RLXiaomi · 7.8B	`Q4_K_M`	8.5 GB	12.1 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 8.3/15	Seed-Coder 8B InstructByteDance · 8.3B	`Q4_K_M`	8.6 GB	11.5 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 8.0/15	EXAONE Deep 7.8BLG AI Research · 7.8B	`Q4_K_M`	8.4 GB	12.1 tok/s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 6.2/15	Qwen3-VL 4B InstructAlibaba · 4.4B	`Q4_K_M`	6.4 GB	21.3 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 8.1/15	Olmo 3 7B ThinkAi2 · 7.3B	`Q4_K_M`	8.4 GB	13.0 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 10.9/15	Mistral Nemo 12B InstructMistral AI · 12B	`Q4_K_M`	11.3 GB	7.8 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 7.5/15	InternVL3 8BShanghai AI Lab · 7.9B	`Q4_K_M`	7.8 GB	11.9 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.2/15	Falcon-H1R 7BTII · 7.6B	`Q4_K_M`	7.5 GB	12.5 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 11.9/15	DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)	`Q4_K_M`	12.4 GB	19.7 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 5.2/15	Granite 4.2 3BIBM · 3.7B	`Q4_K_M`	5.4 GB	25.9 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15	Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)	`Q8_0`	6.6 GB	40.2 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 23.5/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	Qwen2.5 Coder 7B InstructAlibaba · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 7.2/15, Memory use 9.8/15	Falcon 3 10B InstructTII · 10B	`Q4_K_M`	10.2 GB	9.2 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 11.0/15	Pixtral 12B (2409)Mistral AI · 12B	`Q4_K_M`	11.4 GB	7.6 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 5.9/15	Qwen3 4BAlibaba · 4.0B	`Q4_K_M`	6.2 GB	23.6 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	OpenReasoning Nemotron 7BNVIDIA · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 13.7/15	OLMo 2 13B InstructAi2 · 14B	`Q4_K_M`	14.2 GB	6.9 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.5/15	MiniCPM4 8BOpenBMB · 8.2B	`Q4_K_M`	7.8 GB	11.6 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.9/15	Hunyuan 7B InstructTencent · 7.5B	`Q4_K_M`	8.2 GB	12.6 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	Yi 1.5 34B Chat01.AI · 34B	`Q3_K_M`	20.4 GB	3.6 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 9.4/15	Gemma 2 9B ITGoogle · 9.2B	`Q4_K_M`	9.8 GB	10.3 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 4.8/15	North Micro VisionCohere · 2.5B	`Q4_K_M`	5.0 GB	38.2 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15	InternLM2 Chat 20BShanghai AI Lab · 20B	`Q4_K_M`	16.2 GB	4.8 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 12.2/15	Phi-3 Medium 128K InstructMicrosoft · 14B	`Q4_K_M`	12.7 GB	6.8 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 8.1/15	Olmo 3 7B InstructAi2 · 7.3B	`Q4_K_M`	8.4 GB	13.0 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.0/15	MiniCPM-o 2.6 8BOpenBMB · 8.7B	`Q4_K_M`	8.3 GB	10.9 tok/s	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 8.3/15	GLM-4 9B 0414Zhipu AI · 9.4B	`Q4_K_M`	8.6 GB	10.1 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 7.7/15	Qwen2.5-VL 7B InstructAlibaba · 8.3B	`Q4_K_M`	8.0 GB	11.4 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	Qwen2.5 7B InstructAlibaba · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 4.9/15	Nemotron 3 Nano 4BNVIDIA · 4.0B	`Q4_K_M`	5.1 GB	23.9 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	InternVL2.5 8BShanghai AI Lab · 8.1B	`Q4_K_M`	8.5 GB	11.7 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	DeepSeek R1 Distill Llama 8BDeepSeek · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15	InternLM2 Math Plus 20BShanghai AI Lab · 20B	`Q4_K_M`	16.2 GB	4.8 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 11.4/15	Phi-3 Medium (14B)Microsoft · 14B	`Q4_K_M`	11.9 GB	6.8 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 5.1/15	Granite 4.1 3BIBM · 3.4B	`Q4_K_M`	5.3 GB	27.9 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 5.7/15	Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8B	`Q4_K_M`	5.9 GB	24.7 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 7.7/15	Fara 7BMicrosoft · 8.3B	`Q4_K_M`	8.0 GB	11.4 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.0/15	InternLM3 8B InstructShanghai AI Lab · 8.8B	`Q4_K_M`	8.3 GB	10.8 tok/s	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	Qwen2.5 7B Instruct 1MAlibaba · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 14.0/15, Memory use 4.1/15	LFM2.5 2.6BLiquid AI · 2.7B	`Q4_K_M`	4.3 GB	35.1 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.2/15	Falcon-H1 7B InstructTII · 7.6B	`Q4_K_M`	7.5 GB	12.5 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 13.3/15, Memory use 7.4/15	LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)	`Q4_K_M`	7.7 GB	31.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Hermes 3 (Llama 3.1 8B)Nous Research · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Llama 3.1 8B InstructMeta · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 7.8/15	Phi-3.5 Mini InstructMicrosoft · 3.8B	`Q4_K_M`	8.1 GB	24.8 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 8.6/15	GLM-4 9B Chat 1MZhipu AI · 9.5B	`Q4_K_M`	9.0 GB	10.0 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 15.0/15	CogVLM2 Llama 3 Chat 19BZhipu AI · 20B	`Q4_K_M`	18.7 GB	4.9 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 8.3/15	GLM-4 9B Chat (2024)Zhipu AI · 9.4B	`Q4_K_M`	8.6 GB	10.1 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 5.7/15	Phi-4 Mini (3.8B)Microsoft · 3.8B	`Q4_K_M`	5.9 GB	24.7 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	TMax 2BAi2 · 1.9B	`Q5_K_M`	4.0 GB	41.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 13.1/15, Memory use 4.4/15	LFM2.5-VL 3BLiquid AI · 3.1B	`Q4_K_M`	4.6 GB	30.4 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.6/15	MiniCPM-V 2.6 8BOpenBMB · 8.1B	`Q4_K_M`	7.9 GB	11.7 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.5/15	Granite 3.2 8B InstructIBM · 8.2B	`Q4_K_M`	8.8 GB	11.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.5/15	Granite 3.3 8BIBM · 8.2B	`Q4_K_M`	8.8 GB	11.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.8/15, Memory use 10.3/15	DeepSeek Prover V2 7BDeepSeek · 6.9B	`Q4_K_M`	10.8 GB	13.7 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 16.4/45, Memory fit 24.0/25, Speed 5.8/15, Memory use 15.0/15	Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)	`Q2_K`	22.3 GB	6.0 tok/s	Tight fit
61 ptsGood (B) · 61 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 8.3/15	Ministral 8B (2410)Mistral AI · 8.0B	`Q4_K_M`	8.6 GB	11.8 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 5.5/15	Ministral 3 3BMistral AI · 3.9B	`Q4_K_M`	5.7 GB	24.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 8.7/15	Apertus v1.5 8BSwiss AI · 8.9B	`Q4_K_M`	9.0 GB	10.6 tok/s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.9/15, Memory use 4.3/15	Jamba Reasoning 3BAI21 Labs · 3.2B	`Q4_K_M`	4.5 GB	29.6 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Tülu 3 8BAi2 · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 8.0/15	EXAONE 3.5 7.8BLG AI Research · 7.8B	`Q4_K_M`	8.4 GB	12.1 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	Qwen3.5 2BAlibaba · 2.3B	`Q4_K_M`	4.0 GB	41.7 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 4.8/15	SmolLM3 3BHugging Face · 3.1B	`Q4_K_M`	5.0 GB	30.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 9.2/15	Qwen2.5-Omni 7BAlibaba · 11B	`Q4_K_M`	9.5 GB	8.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 7.7/15	Falcon 3 7B InstructTII · 7.5B	`Q4_K_M`	8.0 GB	12.7 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 6.0/15, Memory use 15.0/15	Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)	`Q2_K`	23.3 GB	6.5 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 6.1/15	Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5B	`Q4_K_M`	6.3 GB	21.0 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 6.1/15, Memory use 15.0/15	Qwen1.5 14B ChatAlibaba · 14B	`Q4_K_M`	17.9 GB	6.7 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 5.8/15, Memory use 15.0/15	Mixtral 8x7B InstructMistral AI · 47B (12.9B active)	`Q2_K`	22.3 GB	6.0 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 5.2/15	Gemma 3 4B ITGoogle · 4.3B	`Q4_K_M`	5.4 GB	22.0 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 8.0/15	Phi-3.5 Vision InstructMicrosoft · 4.2B	`Q4_K_M`	8.3 GB	22.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 8.3/15	CodeGeeX4 All 9BZhipu AI · 9.4B	`Q4_K_M`	8.6 GB	10.1 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 13.3/15, Memory use 4.2/15	Jamba2 3BAI21 Labs · 3.0B	`Q4_K_M`	4.4 GB	31.3 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.5/15	Granite 3.1 8B InstructIBM · 8.2B	`Q4_K_M`	8.8 GB	11.6 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 6.7/15	Phi-4 Multimodal InstructMicrosoft · 5.6B	`Q4_K_M`	7.0 GB	17.0 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 12.4/15	StarCoder2 15B InstructBigCode · 16B	`Q4_K_M`	12.9 GB	5.9 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 6.1/15	Hunyuan 4B InstructTencent · 4.2B	`Q4_K_M`	6.3 GB	22.4 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 4.6/15, Memory use 15.0/15	Qwen1.5 32B ChatAlibaba · 33B	`Q3_K_M`	20.6 GB	3.8 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 4.5/15, Memory use 15.0/15	DeepSeek Coder 33B InstructDeepSeek · 33B	`Q3_K_M`	20.9 GB	3.7 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	InternVL2 8BShanghai AI Lab · 8.1B	`Q4_K_M`	8.5 GB	11.7 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Hermes 2 Pro Llama 3 8BNous Research · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	OpenChat 3.6 8BOpenChat · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 5.2/15	MedGemma 4B ITGoogle · 4.3B	`Q4_K_M`	5.4 GB	22.0 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 7.8/15	Phi-3 Small 8K InstructMicrosoft · 7.4B	`Q4_K_M`	8.1 GB	12.8 tok/s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 4.5/15, Memory use 15.0/15	LLaVA 1.6 34BLLaVA · 35B	`Q3_K_M`	20.6 GB	3.5 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 4.0/15, Memory use 15.0/15	Granite Code 34B InstructIBM · 34B	`Q4_K_M`	23.5 GB	2.8 tok/s	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 7.2/15	Gemma 3n E4BGoogle · 7.9B	`Q4_K_M`	7.4 GB	12.1 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 10.0/15	Llama 3.2 11B Vision InstructMeta · 11B	`Q4_K_M`	10.4 GB	8.9 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15	Qwen3-VL 2B InstructAlibaba · 2.1B	`Q4_K_M`	4.8 GB	44.5 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 7.8/15	Phi-3 Mini 128K InstructMicrosoft · 3.8B	`Q4_K_M`	8.1 GB	24.8 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 14.4/15	Granite Code 20B InstructIBM · 20B	`Q4_K_M`	15.0 GB	4.7 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 5.1/15	Granite 4.0 Micro (3B)IBM · 3.4B	`Q4_K_M`	5.3 GB	27.9 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15	Yi 34B Chat01.AI · 34B	`Q3_K_M`	20.4 GB	3.6 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 7.7/15	Qwen2-VL 7B InstructAlibaba · 8.3B	`Q4_K_M`	8.0 GB	11.4 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 8.6/15	Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4B	`Q4_K_M`	9.0 GB	11.3 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.3/15	Qwen2 7B InstructAlibaba · 7.6B	`Q4_K_M`	7.6 GB	12.4 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 7.8/15	Aya Vision 8BCohere · 8.6B	`Q4_K_M`	8.2 GB	11.0 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.5/15	Command R7BCohere · 8.0B	`Q4_K_M`	7.8 GB	11.8 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Llama 3 8B InstructMeta · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
59 ptsGood (B) · 59 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 15.0/15	Code Llama 13B InstructMeta · 13B	`Q4_K_M`	17.2 GB	7.3 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 10.5/15	DeepSeek Coder 6.7B InstructDeepSeek · 6.7B	`Q4_K_M`	10.9 GB	14.1 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 8.0/15	Phi-3 Vision 128K InstructMicrosoft · 4.2B	`Q4_K_M`	8.3 GB	22.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 9.5/15	Nous Hermes 2 SOLAR 10.7BNous Research · 11B	`Q4_K_M`	9.9 GB	8.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 9.5/15	SOLAR 10.7B InstructUpstage · 11B	`Q4_K_M`	9.9 GB	8.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.5/15	Command R7B ArabicCohere · 8.0B	`Q4_K_M`	7.8 GB	11.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 5.7/15	AFM 4.5BArcee AI · 4.6B	`Q4_K_M`	5.9 GB	20.5 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.9/15, Memory use 4.4/15	Granite 4.0 H MicroIBM · 3.2B	`Q4_K_M`	4.5 GB	29.7 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 11.0/15	CodeGemma 7BGoogle · 8.5B	`Q4_K_M`	11.5 GB	11.1 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Apertus 8B InstructSwiss AI · 8.1B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 6.2/15	Phi-3 Mini 4K InstructMicrosoft · 3.8B	`Q4_K_M`	6.5 GB	24.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Aya Expanse 8BCohere · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 8.0/15	InternLM2.5 7B ChatShanghai AI Lab · 7.7B	`Q4_K_M`	8.3 GB	12.2 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.4/15	Yi Coder 9B Chat01.AI · 8.8B	`Q4_K_M`	8.7 GB	10.7 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15	LFM2.5 1.2B InstructLiquid AI · 1.2B	`Q8_0`	3.9 GB	41.2 tok/s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 7.9/15	Granite 3.0 8B InstructIBM · 8.2B	`Q4_K_M`	8.2 GB	11.6 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 4.1/15	LFM2 2.6BLiquid AI · 2.6B	`Q4_K_M`	4.2 GB	36.9 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 4.5/15	Falcon-H1 3B InstructTII · 3.2B	`Q4_K_M`	4.7 GB	30.1 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 14.4/45, Memory fit 24.0/25, Speed 4.5/15, Memory use 15.0/15	Code Llama 34B InstructMeta · 34B	`Q3_K_M`	20.7 GB	3.6 tok/s	Tight fit
57 ptsUsable (C) · 57 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 5.1/15	MiniCPM3 4BOpenBMB · 4.1B	`Q4_K_M`	5.3 GB	23.3 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 13.2/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 4.8/15	Llama 3.2 3B InstructMeta · 3.2B	`Q3_K_M`	5.0 GB	38.1 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 13.6/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 4.2/15	Qwen2.5 Coder 3B InstructAlibaba · 3.1B	`Q3_K_M`	4.3 GB	39.6 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 8.8/15	OLMo 2 7B InstructAi2 · 7.3B	`Q4_K_M`	9.1 GB	13.0 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Mistral 7B Instruct v0.3Mistral AI · 7.3B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 7.0/15	OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)	`Q4_K_M`	7.3 GB	36.4 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	Qwen3 1.7BAlibaba · 2.0B	`Q4_K_M`	4.7 GB	46.7 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	EXAONE 4.0 1.2BLG AI Research · 1.3B	`Q6_K`	4.1 GB	51.3 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 7.5/15	Zamba2 7B InstructZyphra · 7.4B	`Q4_K_M`	7.8 GB	12.9 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 10.5/15	SQLCoder 7B v2Defog · 6.7B	`Q4_K_M`	10.9 GB	14.1 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 6.1/15	Voxtral Mini 3BMistral AI · 4.7B	`Q4_K_M`	6.4 GB	20.2 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 4.4/15	EXAONE 3.5 2.4BLG AI Research · 2.4B	`Q4_K_M`	4.6 GB	39.3 tok/s	Runs well
57 ptsUsable (C) · 57 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 7.5/15	EXAONE 3.0 7.8B InstructLG AI Research · 7.8B	`Q4_K_M`	7.8 GB	12.1 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 11.0/15	DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)	`Q3_K_M`	11.5 GB	21.9 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 4.2/15	Qwen2.5 3B InstructAlibaba · 3.1B	`Q3_K_M`	4.3 GB	39.6 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 4.6/15	Granite 3.2 2B InstructIBM · 2.5B	`Q4_K_M`	4.7 GB	37.4 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 4.6/15	Granite 3.3 2BIBM · 2.5B	`Q4_K_M`	4.7 GB	37.4 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 12.4/15	StarCoder2 15B (base)BigCode · 16B	`Q4_K_M`	12.9 GB	5.9 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Hermes 2 Pro Mistral 7BNous Research · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Starling LM 7B BetaNexusflow · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 13.3/15	Orca 2 13BMicrosoft · 13B	`Q4_K_M`	13.8 GB	7.3 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 4.8/15	Hermes 3 Llama 3.2 3BNous Research · 3.2B	`Q3_K_M`	5.0 GB	38.1 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 6.7/15	Falcon3 Mamba 7B InstructTII · 7.3B	`Q4_K_M`	7.0 GB	13.0 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 4.9/15	Qwen2.5-VL 3B InstructAlibaba · 3.8B	`Q4_K_M`	5.1 GB	25.3 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 15.0/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	OpenChat 3.5 (0106)OpenChat · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 8.0/15	Yi 1.5 9B Chat01.AI · 8.8B	`Q4_K_M`	8.3 GB	10.7 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15	Granite 4.0 H 1BIBM · 1.5B	`Q6_K`	3.8 GB	45.0 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 13.8/15	Baichuan 2 13B ChatBaichuan · 14B	`Q4_K_M`	14.4 GB	6.8 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 9.1/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 10.7/15	Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)	`Q3_K_M`	11.1 GB	22.7 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 4.6/15	Granite 3.1 2B InstructIBM · 2.5B	`Q4_K_M`	4.7 GB	37.4 tok/s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 5.7/15	Gemma 3n E2BGoogle · 5.4B	`Q4_K_M`	6.0 GB	17.4 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 11.0/15	Gemma 1.1 7B ITGoogle · 8.5B	`Q4_K_M`	11.5 GB	11.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.1/15	Qwen2.5-Math 7B InstructAlibaba · 7.6B	`Q4_K_M`	7.4 GB	12.4 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.2/15	Aya 23 8BCohere · 8.0B	`Q4_K_M`	8.5 GB	11.8 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Mistral 7B Instruct v0.2Mistral AI · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Nous Hermes 2 Mistral 7B DPONous Research · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	OpenChat 3.5 (1210)OpenChat · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Mathstral 7BMistral AI · 7.3B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 13.3/15	Llama 2 13B ChatMeta · 13B	`Q4_K_M`	13.8 GB	7.3 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 4.4/15	Gemma 2 2BGoogle · 2.6B	`Q4_K_M`	4.6 GB	36.3 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 6.7/15	Codestral Mamba 7BMistral AI · 7.3B	`Q4_K_M`	7.0 GB	13.0 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 4.7/15	Falcon 3 3B InstructTII · 3.2B	`Q3_K_M`	4.8 GB	37.9 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 10.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15	SmolVLM2 2.2B InstructHugging Face · 2.3B	`Q4_K_M`	5.5 GB	42.1 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 11.1/15	Qwen1.5 7B ChatAlibaba · 7.7B	`Q4_K_M`	11.5 GB	12.3 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	Qwen2.5 Coder 1.5B InstructAlibaba · 1.5B	`Q6_K`	4.0 GB	42.7 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	Falcon-H1 1.5B InstructTII · 1.6B	`Q6_K`	4.0 GB	42.4 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15	LFM2 1.2BLiquid AI · 1.2B	`Q8_0`	3.9 GB	41.2 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	DeepScaleR 1.5B PreviewAgentica · 1.8B	`Q5_K_M`	4.0 GB	44.0 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 8.2/15	RecurrentGemma 9B ITGoogle · 9.6B	`Q4_K_M`	8.5 GB	9.8 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.3/15	Granite Code 8B Instruct (128K)IBM · 8.1B	`Q4_K_M`	8.6 GB	11.8 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15	Qwen3.5 0.8BAlibaba · 0.9B	`Q8_0`	3.5 GB	55.4 tok/s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 11.0/15	Gemma 7B ITGoogle · 8.5B	`Q4_K_M`	11.5 GB	11.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 8.0/15	InternLM2 Math Plus 7BShanghai AI Lab · 7.7B	`Q4_K_M`	8.3 GB	12.2 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	OpenHermes 2.5 Mistral 7BTeknium · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Starling LM 7B AlphaBerkeley · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 9.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15	SmolVLM 2.2B InstructHugging Face · 2.3B	`Q4_K_M`	5.5 GB	42.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 4.3/15	Granite 3.0 2B InstructIBM · 2.6B	`Q4_K_M`	4.5 GB	36.0 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 10.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	Qwen2.5 1.5B InstructAlibaba · 1.5B	`Q6_K`	4.0 GB	42.7 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 10.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	LFM2-VL 1.6BLiquid AI · 1.6B	`Q6_K`	3.9 GB	41.6 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 8.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15	Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)	`Q6_K`	5.8 GB	41.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	Granite Vision 3.2 2BIBM · 3.0B	`Q3_K_M`	4.7 GB	41.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 10.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	Qwen2-VL 2B InstructAlibaba · 2.2B	`Q4_K_M`	4.1 GB	42.9 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 9.4/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 13.5/15	LLaVA 1.5 13BLLaVA · 13B	`Q4_K_M`	14.0 GB	7.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Mistral 7B Instruct v0.1Mistral AI · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 9.4/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 13.3/15	WizardLM 13B v1.2WizardLM · 13B	`Q4_K_M`	13.8 GB	7.3 tok/s	Runs well
54 ptsUsable (C) · 54 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 3.9/15, Memory use 15.0/15	Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50B	`Q2_K`	25.2 GB	2.7 tok/s	Runs with offload
53 ptsUsable (C) · 53 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 10.4/15	StableLM 2 12B ChatStability AI · 12B	`Q4_K_M`	10.8 GB	7.8 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 9.1/45, Memory fit 25.0/25, Speed 10.1/15, Memory use 9.7/15	Code Llama 7B InstructMeta · 6.7B	`Q3_K_M`	10.1 GB	18.2 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15	Stable Code Instruct 3BStability AI · 2.8B	`Q3_K_M`	6.6 GB	43.7 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15	SmolLM2 1.7B InstructHugging Face · 1.7B	`Q5_K_M`	5.3 GB	45.8 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 11.9/15	StarCoder 15BBigCode · 16B	`Q4_K_M`	12.3 GB	6.0 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 9.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15	Hunyuan 1.8B InstructTencent · 1.8B	`Q5_K_M`	4.3 GB	43.7 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 6.0/15	Qwen2.5-Omni 3BAlibaba · 5.5B	`Q4_K_M`	6.2 GB	17.1 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 9.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8B	`Q5_K_M`	4.0 GB	44.0 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15	Llama 3.2 1B InstructMeta · 1.2B	`Q6_K`	3.8 GB	53.0 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15	Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)	`Q6_K`	5.6 GB	41.1 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 6.6/15	Granite Code 3B Instruct (128K)IBM · 3.5B	`Q3_K_M`	6.9 GB	35.2 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 7.9/15	LLaVA 1.6 Mistral 7BLLaVA · 7.6B	`Q4_K_M`	8.2 GB	12.5 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Neural Chat 7B v3.3Intel · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 8.6/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 13.3/15	Vicuna 13B v1.5LMSYS · 13B	`Q4_K_M`	13.8 GB	7.3 tok/s	Runs well
53 ptsUsable (C) · 53 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 6.7/15	Falcon Mamba 7B InstructTII · 7.3B	`Q4_K_M`	7.0 GB	13.0 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 9.4/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 4.3/15	Zamba2 2.7B InstructZyphra · 2.7B	`Q4_K_M`	4.5 GB	35.6 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 8.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	Qwen2.5-Math 1.5B InstructAlibaba · 1.5B	`Q6_K`	3.9 GB	42.7 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 6.2/15	Yi 1.5 6B Chat01.AI · 6.1B	`Q4_K_M`	6.5 GB	15.6 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15	Gemma 3 1BGoogle · 1.0B	`Q8_0`	3.6 GB	48.2 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	WizardMath 7B v1.1WizardLM · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.7/15	Zephyr 7B BetaHugging Face · 7.2B	`Q4_K_M`	8.0 GB	13.1 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 7.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	InternLM2.5 1.8B ChatShanghai AI Lab · 1.9B	`Q5_K_M`	4.7 GB	41.4 tok/s	Runs well
52 ptsUsable (C) · 52 of 100 points: Model quality 7.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15	Yi Coder 1.5B Chat01.AI · 1.5B	`Q6_K`	5.3 GB	44.4 tok/s	Runs well
51 ptsUsable (C) · 51 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15	LFM2 700MLiquid AI · 0.7B	`Q8_0`	3.4 GB	65.2 tok/s	Runs well
51 ptsUsable (C) · 51 of 100 points: Model quality 7.1/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 4.3/15	Falcon 3 1B InstructTII · 1.7B	`Q6_K`	4.5 GB	39.3 tok/s	Runs well
51 ptsUsable (C) · 51 of 100 points: Model quality 8.3/45, Memory fit 25.0/25, Speed 10.1/15, Memory use 7.7/15	Orca 2 7BMicrosoft · 6.7B	`Q3_K_M`	8.0 GB	18.2 tok/s	Runs well
51 ptsUsable (C) · 51 of 100 points: Model quality 6.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15	StableLM Zephyr 3BStability AI · 2.8B	`Q3_K_M`	5.2 GB	43.7 tok/s	Runs well
51 ptsUsable (C) · 51 of 100 points: Model quality 10.3/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 7.1/15	StarCoder2 7BBigCode · 7.2B	`Q4_K_M`	7.4 GB	13.2 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 7.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15	Qwen2 1.5B InstructAlibaba · 1.5B	`Q6_K`	4.0 GB	42.7 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.9/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 4.6/15	Nemotron Mini 4B InstructNVIDIA · 4.2B	`Q2_K`	4.7 GB	37.1 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15	StarCoder2 3BBigCode · 3.0B	`Q3_K_M`	4.3 GB	40.4 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15	Phi-2 2.7BMicrosoft · 2.8B	`Q3_K_M`	4.6 GB	44.0 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15	Qwen3 0.6BAlibaba · 0.8B	`Q8_0`	4.3 GB	64.3 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15	DeepSeek Coder 1.3B InstructDeepSeek · 1.4B	`Q6_K`	5.2 GB	48.7 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15	OLMo 2 1B InstructAi2 · 1.5B	`Q6_K`	4.3 GB	44.4 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 8.0/15	Baichuan 2 7B ChatBaichuan · 7.5B	`Q3_K_M`	8.3 GB	16.3 tok/s	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 6.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15	SmolLM 1.7B InstructHugging Face · 1.7B	`Q5_K_M`	4.1 GB	45.8 tok/s	Runs well
49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15	Falcon-H1 0.5B InstructTII · 0.5B	`F16`	3.7 GB	42.7 tok/s	Runs well
49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 7.1/15	Llama 2 7B ChatMeta · 6.7B	`Q2_K`	7.4 GB	23.1 tok/s	Runs well
49 ptsUsable (C) · 49 of 100 points: Model quality 5.0/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	Falcon 40B InstructTII · 42B	`Q2_K`	19.5 GB	3.7 tok/s	Runs well
49 ptsUsable (C) · 49 of 100 points: Model quality 6.0/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 4.0/15	CodeGemma 2BGoogle · 2.5B	`Q4_K_M`	4.2 GB	37.7 tok/s	Runs well
49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15	LFM2.5 350MLiquid AI · 0.4B	`F16`	3.3 GB	63.5 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	StableLM 2 1.6B ChatStability AI · 1.6B	`Q6_K`	4.7 GB	40.1 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	StableLM 2 Zephyr 1.6BStability AI · 1.6B	`Q6_K`	4.7 GB	40.1 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.7/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 7.0/15	DeepSeek LLM 7B ChatDeepSeek · 6.9B	`Q2_K`	7.3 GB	22.5 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15	LFM2-VL 450MLiquid AI · 0.5B	`F16`	3.5 GB	49.4 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 4.0/15	Gemma 2B ITGoogle · 2.5B	`Q4_K_M`	4.2 GB	37.7 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15	LFM2 350MLiquid AI · 0.4B	`F16`	3.3 GB	63.5 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	Granite 4.0 H 350MIBM · 0.3B	`F16`	3.2 GB	65.4 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 5.0/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 7.2/15	LLaVA 1.5 7BLLaVA · 7.1B	`Q2_K`	7.5 GB	22.0 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 5.0/15	Yi 6B Chat01.AI · 6.1B	`Q2_K`	5.2 GB	25.7 tok/s	Runs well
48 ptsUsable (C) · 48 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15	SmolVLM 500M InstructHugging Face · 0.5B	`F16`	3.9 GB	43.6 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15	Qwen2.5 0.5B InstructAlibaba · 0.5B	`F16`	3.6 GB	45.3 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 4.4/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 7.1/15	Vicuna 7B v1.5LMSYS · 6.7B	`Q2_K`	7.4 GB	23.1 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15	Hunyuan 0.5B InstructTencent · 0.5B	`F16`	4.4 GB	41.1 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	LFM2.5 230MLiquid AI · 0.2B	`F16`	3.1 GB	96.6 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15	Qwen2.5 Coder 0.5B InstructAlibaba · 0.5B	`F16`	3.6 GB	45.3 tok/s	Runs well
47 ptsUsable (C) · 47 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15	SmolLM2 360M InstructHugging Face · 0.4B	`F16`	3.6 GB	61.7 tok/s	Runs well
46 ptsUsable (C) · 46 of 100 points: Model quality 4.4/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 6.1/15	OLMo 7B InstructAi2 · 6.9B	`Q2_K`	6.3 GB	22.6 tok/s	Runs well
46 ptsUsable (C) · 46 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15	TinyLlama 1.1B ChatTinyLlama · 1.1B	`Q8_0`	3.7 GB	43.8 tok/s	Runs well
46 ptsUsable (C) · 46 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15	Qwen2 0.5B InstructAlibaba · 0.5B	`F16`	3.6 GB	45.3 tok/s	Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 3.8/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 6.3/15	InternLM 7BShanghai AI Lab · 7.3B	`Q2_K`	6.5 GB	21.2 tok/s	Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15	ERNIE 4.5 0.3BBaidu · 0.4B	`F16`	3.4 GB	61.7 tok/s	Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 5.2/15, Memory use 15.0/15	Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)	`Q2_K`	26.0 GB	4.7 tok/s	Runs with offload
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	SmolVLM 256M InstructHugging Face · 0.3B	`F16`	3.2 GB	85.5 tok/s	Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15	Gemma 3 270MGoogle · 0.3B	`F16`	3.1 GB	82.3 tok/s	Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15	SmolLM 360M InstructHugging Face · 0.4B	`F16`	3.3 GB	61.7 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15	SmolLM2 135M InstructHugging Face · 0.1B	`F16`	3.0 GB	171 tok/s	Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	Falcon-H1 Tiny 90M InstructTII · 0.1B	`F16`	2.8 GB	247 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	SmolLM 135M InstructHugging Face · 0.1B	`F16`	2.8 GB	171 tok/s	Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 1.9/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 5.2/15	Falcon 7B InstructTII · 7.2B	`Q2_K`	5.4 GB	21.5 tok/s	Runs well
40 ptsPoor (D) · 40 of 100 points: Model quality 17.0/45, Memory fit 4.0/25, Speed 4.6/15, Memory use 15.0/15	Command R 35B (v01)Cohere · 35B	`Q2_K`	27.2 GB	3.8 tok/s	Heavy offload
39 ptsPoor (D) · 39 of 100 points: Model quality 15.8/45, Memory fit 4.0/25, Speed 4.6/15, Memory use 15.0/15	Aya 23 35BCohere · 35B	`Q2_K`	27.2 GB	3.8 tok/s	Heavy offload
11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	gpt-oss 120BOpenAI · 117B (5.1B active)	`MXFP4`	69.4 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiMo V2.6 Pro (1T-A42B)Xiaomi · 1,024B (42.0B active)	`Q2_K`	413 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3.8 Max (2.4T-A95B)Alibaba · 2,446B (95.0B active)	`Q2_K`	982 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K3 (2.8T)Moonshot AI · 2,780B (104.0B active)	`Q2_K`	1,115 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active)	`Q2_K`	305 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active)	`Q2_K`	127 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V4 Pro (1.6T-A49B)DeepSeek · 1,651B (49.0B active)	`Q2_K`	663 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active)	`Q2_K`	74.7 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active)	`Q2_K`	305 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hunyuan Hy4 Preview (780B)Tencent · 780B (55.0B active)	`Q2_K`	315 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2.6 (1T)Moonshot AI · 1,027B (32.0B active)	`Q2_K`	414 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-5.3 Flash (320B-A18B)Zhipu AI · 321B (18.0B active)	`Q2_K`	131 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-5.1 (744B-A40B)Zhipu AI · 754B (40.0B active)	`Q2_K`	305 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V4 Pro (April 2026)DeepSeek · 1,599B (49.0B active)	`Q2_K`	643 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3.5 397B-A17BAlibaba · 403B (17.0B active)	`Q2_K`	164 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax M3 (427B)MiniMax · 427B (25.0B active)	`Q2_K`	174 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-5 (744B-A40B)Zhipu AI · 754B (40.0B active)	`Q2_K`	305 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active)	`Q2_K`	125 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2.5 (1T)Moonshot AI · 1,027B (32.0B active)	`Q2_K`	414 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active)	`Q2_K`	414 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active)	`Q2_K`	125 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Ornith 1.5 397B-A17BDeepReinforce · 403B (17.0B active)	`Q2_K`	164 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3.2 (671B)DeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.7 (355B-A32B)Zhipu AI · 358B (32.0B active)	`Q2_K`	149 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active)	`Q2_K`	96.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Nemotron 3 Ultra 550B-A55BNVIDIA · 561B (55.0B active)	`Q2_K`	227 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek R1 0528 (671B)DeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2 Thinking (1T)Moonshot AI · 1,026B (32.0B active)	`Q2_K`	414 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3.2 ExpDeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active)	`Q2_K`	96.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek R1 (671B)DeepSeek · 671B (37.0B active)	`Q2_K`	271 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active)	`Q2_K`	119 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)	`Q2_K`	52.8 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active)	`Q2_K`	82.7 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3.1 TerminusDeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3.1 (671B)DeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2 Instruct 0905 (1T)Moonshot AI · 1,026B (32.0B active)	`Q2_K`	414 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active)	`Q2_K`	96.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active)	`Q2_K`	98.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active)	`Q2_K`	197 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active)	`Q2_K`	127 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active)	`Q2_K`	405 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mistral Large 3 (675B)Mistral AI · 675B (41.0B active)	`Q2_K`	273 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active)	`Q2_K`	98.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Solar Open 2 250BUpstage · 250B (15.0B active)	`Q2_K`	104 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active)	`Q2_K`	414 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active)	`Q2_K`	96.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3-VL 235B-A22B InstructAlibaba · 236B (22.0B active)	`Q2_K`	98.4 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active)	`Q2_K`	97.8 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	LongCat Flash Chat (560B)Meituan · 562B (27.0B active)	`Q2_K`	228 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active)	`Q2_K`	52.0 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 235B-A22BAlibaba · 235B (22.0B active)	`Q2_K`	98.1 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Devstral 2 (123B)Mistral AI · 125B	`Q2_K`	55.5 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active)	`Q2_K`	100 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active)	`Q2_K`	51.2 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 253B	`Q2_K`	108 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active)	`Q2_K`	34.6 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)	`Q2_K`	35.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Baichuan M3 235B-A22BBaichuan · 235B (22.0B active)	`Q2_K`	98.1 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.6 (355B-A32B)Zhipu AI · 357B (32.0B active)	`Q2_K`	148 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active)	`Q2_K`	35.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3 0324 (671B)DeepSeek · 685B (37.0B active)	`Q2_K`	277 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.6VZhipu AI · 108B (12.0B active)	`Q2_K`	47.1 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax-M1 80KMiniMax · 456B (45.9B active)	`Q2_K`	185 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Command A Reasoning (111B)Cohere · 111B	`Q2_K`	47.7 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.5 (355B-A32B)Zhipu AI · 358B (32.0B active)	`Q2_K`	149 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active)	`Q2_K`	53.9 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.3 70B InstructMeta · 71B	`Q2_K`	33.4 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax-M1 40KMiniMax · 456B (45.9B active)	`Q2_K`	185 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active)	`Q2_K`	50.5 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mistral Medium 3.5 (128B)Mistral AI · 128B	`Q2_K`	56.6 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Trinity Large Thinking (400B-A13B)Arcee AI · 399B (13.0B active)	`Q2_K`	163 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Command A (111B)Cohere · 111B	`Q2_K`	47.7 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active)	`Q2_K`	125 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.5VZhipu AI · 108B (12.0B active)	`Q2_K`	47.1 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hermes 4 405BNous Research · 406B	`Q2_K`	169 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Kimi Dev 72BMoonshot AI · 73B	`Q2_K`	34.3 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mistral Large 2.1 (2411)Mistral AI · 123B	`Q2_K`	54.5 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Solar Open 100BUpstage · 103B (12.0B active)	`Q2_K`	45.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)	`Q2_K`	48.3 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mistral Large 2 (123B)Mistral AI · 123B	`Q2_K`	54.7 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Pixtral Large 124B (2411)Mistral AI · 124B	`Q2_K`	55.1 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)	`Q2_K`	44.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	dots.llm1 Instructrednote · 143B (14.0B active)	`Q2_K`	67.9 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)	`Q2_K`	44.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	MiniMax-Text-01MiniMax · 456B (45.9B active)	`Q2_K`	185 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Tülu 3 405BAi2 · 406B	`Q2_K`	169 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V3 (671B)DeepSeek · 671B (37.0B active)	`Q2_K`	271 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Sarvam 105BSarvam AI · 106B (10.0B active)	`Q2_K`	45.2 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek Coder V2 (236B)DeepSeek · 236B (21.0B active)	`Q2_K`	97.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hermes 4 70BNous Research · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)	`Q2_K`	35.7 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	InternVL3 78BShanghai AI Lab · 78B	`Q2_K`	36.6 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Leanstral 119B-A6BMistral AI · 119B (6.5B active)	`Q2_K`	50.5 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen2.5 72B InstructAlibaba · 73B	`Q2_K`	34.3 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen2.5-VL 72B InstructAlibaba · 73B	`Q2_K`	34.6 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active)	`Q2_K`	97.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek R1 Distill Llama 70BDeepSeek · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V2.5 1210DeepSeek · 236B (21.0B active)	`Q2_K`	97.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.1 405B InstructMeta · 406B	`Q2_K`	169 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 4 Maverick (17B x 128E)Meta · 402B (17.0B active)	`Q2_K`	165 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 4 Scout 17B-16EMeta · 109B (17.0B active)	`Q2_K`	47.6 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Tülu 3 70BAi2 · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Command R+ (08-2024) 104BCohere · 104B	`Q2_K`	46.2 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V2.5DeepSeek · 236B (21.0B active)	`Q2_K`	97.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Jamba 1.5 LargeAI21 Labs · 399B (94.0B active)	`Q2_K`	162 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.1 70B InstructMeta · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Hermes 3 (Llama 3.1 70B)Nous Research · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	QVQ 72B PreviewAlibaba · 73B	`Q2_K`	34.6 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Apertus v1.5 70BSwiss AI · 72B	`Q2_K`	34.0 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.1 Nemotron 70B InstructNVIDIA · 71B	`Q2_K`	33.4 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3.2 90B Vision InstructMeta · 89B	`Q2_K`	41.3 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Command R+ 104B (04-2024)Cohere · 104B	`Q2_K`	46.2 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen2 72B InstructAlibaba · 73B	`Q2_K`	34.3 GB	—	Won't run
6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen2-VL 72B InstructAlibaba · 73B	`Q2_K`	34.6 GB	—	Won't run
5 ptsWon't run (F) · 5 of 100 points: Model quality 5.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek V2 ChatDeepSeek · 236B (21.0B active)	`Q2_K`	97.4 GB	—	Won't run
5 ptsWon't run (F) · 5 of 100 points: Model quality 5.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Apertus 70B InstructSwiss AI · 71B	`Q2_K`	33.4 GB	—	Won't run
5 ptsWon't run (F) · 5 of 100 points: Model quality 5.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 3 70B InstructMeta · 71B	`Q2_K`	33.4 GB	—	Won't run
5 ptsWon't run (F) · 5 of 100 points: Model quality 5.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen2.5-Math 72B InstructAlibaba · 73B	`Q2_K`	32.9 GB	—	Won't run
5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Mixtral 8x22B InstructMistral AI · 141B (39.0B active)	`Q2_K`	60.7 GB	—	Won't run
4 ptsWon't run (F) · 4 of 100 points: Model quality 4.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Qwen1.5 110B ChatAlibaba · 111B	`Q2_K`	49.7 GB	—	Won't run
4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Grok-1 (314B)xAI · 314B (86.0B active)	`Q2_K`	130 GB	—	Won't run
4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Snowflake Arctic InstructSnowflake · 479B (17.0B active)	`Q2_K`	195 GB	—	Won't run
4 ptsWon't run (F) · 4 of 100 points: Model quality 4.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Code Llama 70B InstructMeta · 69B	`Q2_K`	31.5 GB	—	Won't run
3 ptsWon't run (F) · 3 of 100 points: Model quality 3.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	DeepSeek LLM 67B ChatDeepSeek · 67B	`Q2_K`	31.1 GB	—	Won't run
3 ptsWon't run (F) · 3 of 100 points: Model quality 3.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Llama 2 70B ChatMeta · 69B	`Q2_K`	31.5 GB	—	Won't run
3 ptsWon't run (F) · 3 of 100 points: Model quality 3.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Falcon 180B ChatTII · 180B	`Q2_K`	74.7 GB	—	Won't run

Image models on your AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs · 9.1B	`FP8`	19.9 GB	5.9 s	Runs well
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs · 3.9B	`FP16`	18.1 GB	3.6 s	Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 12.5/15	Z-Image TurboAlibaba (Tongyi) · 6.2B	`Q8 GGUF`	13.0 GB	10 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.1 [schnell]Black Forest Labs · 11.9B	`FP8`	19.6 GB	6.5 s	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 15.0/15	FLUX.1 Krea [dev]Black Forest Labs · 11.9B	`FP8`	19.6 GB	39 s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 15.0/15	FLUX.1 [dev]Black Forest Labs · 11.9B	`FP8`	19.6 GB	39 s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Stable Diffusion 3.5 Large TurboStability AI · 8.1B	`Q8 GGUF`	16.8 GB	6.7 s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15	FLUX.1 Kontext [dev]Black Forest Labs · 11.9B	`FP8`	20.2 GB	72 s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 15.0/15	FLUX.1 Fill [dev]Black Forest Labs · 11.9B	`FP8`	19.6 GB	41 s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 5.9/15, Memory use 15.0/15	Chroma1-HDLodestone Rock · 8.9B	`FP8`	16.4 GB	65 s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 12.1/15	Z-ImageAlibaba (Tongyi) · 6.2B	`FP8`	12.6 GB	56 s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 15.0/15	CogView4 6BZhipu AI · 6.4B	`FP8`	18.2 GB	59 s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15	Stable Diffusion 3.5 LargeStability AI · 8.1B	`FP8`	16.3 GB	36 s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 33.5/45, Memory fit 20.0/25, Speed 8.1/15, Memory use 15.0/15	HiDream-I1 FastHiDream.ai · 17.1B	`FP8`	20.1 GB	34 s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 35.3/45, Memory fit 20.0/25, Speed 6.2/15, Memory use 15.0/15	HiDream-I1 DevHiDream.ai · 17.1B	`FP8`	20.1 GB	58 s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 15.0/15	OmniGen2BAAI (VectorSpaceLab) · 4.0B	`FP16`	18.0 GB	58 s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 37.0/45, Memory fit 20.0/25, Speed 3.8/15, Memory use 15.0/15	HiDream-I1 FullHiDream.ai · 17.1B	`FP8`	20.1 GB	2.6 min	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 38.5/45, Memory fit 18.0/25, Speed 3.7/15, Memory use 15.0/15	FLUX.2 [dev]Black Forest Labs · 32.2B	`Q4 GGUF`	22.8 GB	2.7 min	Tight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 13.1/15, Memory use 10.6/15	KolorsKuaishou · 2.6B	`FP8`	11.0 GB	13 s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 37.7/45, Memory fit 20.0/25, Speed 2.3/15, Memory use 15.0/15	Qwen-Image 2512Alibaba · 20.4B	`Q4 GGUF`	18.6 GB	6.9 min	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15	PixArt-Σ XL 1024PixArt · 0.6B	`FP16`	12.8 GB	5.4 s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15	DreamShaper XL v2 TurboLykon · 2.6B	`FP16`	8.9 GB	4.7 s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 9.4/15, Memory use 12.2/15	Lumina-Image 2.0Shanghai AI Lab · 2.6B	`FP16`	12.7 GB	25 s	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 2.5/15, Memory use 15.0/15	Qwen-Image-Edit 2511Alibaba · 20.4B	`Q4 GGUF`	16.0 GB	6.1 min	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15	SDXL-Lightning (4-step)ByteDance · 2.6B	`FP16`	8.9 GB	2.5 s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 6.7/15, Memory use 15.0/15	AuraFlow v0.3fal · 6.9B	`FP16`	18.5 GB	51 s	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 9.5/15	Stable Diffusion 3 MediumStability AI · 2.0B	`FP8`	9.9 GB	10 s	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 10.0/15	Stable Diffusion 3.5 MediumStability AI · 2.5B	`FP8`	10.4 GB	20 s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 27.3/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 5.3/15	Juggernaut XL v9RunDiffusion · 2.6B	`FP8`	5.6 GB	15 s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 27.3/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 5.3/15	RealVisXL V5.0SG161222 · 2.6B	`FP8`	5.6 GB	15 s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 9.1/15, Memory use 8.6/15	Playground v2.5Playground AI · 2.6B	`FP16`	8.9 GB	27 s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 5.3/15	Animagine XL 4.0Cagliostro Lab · 2.6B	`FP8`	5.6 GB	14 s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 5.3/15	Illustrious XL v0.1OnomaAI · 2.6B	`FP8`	5.6 GB	14 s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 13.5/15, Memory use 5.3/15	Pony Diffusion V6 XLPurpleSmartAI · 2.6B	`FP8`	5.6 GB	12 s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 24.7/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 5.3/15	Animagine XL 3.1Cagliostro Lab · 2.6B	`FP8`	5.6 GB	14 s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 8.9/15	Hunyuan-DiT v1.2Tencent · 1.5B	`FP16`	9.3 GB	22 s	Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 11.7/15, Memory use 7.8/15	Stable CascadeStability AI · 5.2B	`FP8`	8.1 GB	16 s	Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 5.3/15	Stable Diffusion XL 1.0Stability AI · 2.6B	`FP8`	5.6 GB	15 s	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 38.8/45, Memory fit 12.0/25, Speed 2.4/15, Memory use 12.8/15	Qwen-ImageAlibaba · 20.4B	`FP8`	13.3 GB	6.4 min	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15	SDXL TurboStability AI · 2.6B	`FP16`	7.6 GB	0.5 s	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	Realistic Vision V5.1SG161222 · 0.9B	`FP16`	2.8 GB	4.4 s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	DreamShaper 8Lykon · 0.9B	`FP16`	2.8 GB	4.4 s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	Stable Diffusion 1.5Stability AI / Runway · 0.9B	`FP16`	2.8 GB	4.4 s	Runs well
58 ptsGood (B) · 58 of 100 points: Model quality 21.6/45, Memory fit 20.0/25, Speed 8.1/15, Memory use 8.3/15	Kandinsky 3Sber AI · 3.0B	`FP16`	8.7 GB	34 s	Runs well
56 ptsUsable (C) · 56 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15	LCM DreamShaper v7Tsinghua (LCM) · 0.9B	`FP16`	2.8 GB	0.9 s	Runs well
55 ptsUsable (C) · 55 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15	SD TurboStability AI · 0.9B	`FP16`	3.3 GB	0.3 s	Runs well
11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	HunyuanImage 3.0 (80B-A13B)Tencent · 83.0B	`FP8`	32.8 GB	—	Won't run

Video models on your AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	LTX-Video 2BLightricks · 1.9B	`FP16`	17.5 GB	1.5 min	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 5.4/15, Memory use 15.0/15	FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9B	`FP8`	19.6 GB	22.9 min	Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 31.8/45, Memory fit 23.0/25, Speed 3.0/15, Memory use 15.0/15	Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3B	`Q4 GGUF`	21.6 GB	72.6 min	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 31.0/45, Memory fit 23.0/25, Speed 3.2/15, Memory use 15.0/15	Wan 2.1 I2V 14B 480PAlibaba · 14.0B	`Q4 GGUF`	20.6 GB	65.4 min	Tight fit
71 ptsGood (B) · 71 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 14.3/15	CogVideoX 5B I2VZhipu AI · 5.6B	`FP8`	14.9 GB	9.8 min	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 6.8/15, Memory use 15.0/15	Wan 2.1 T2V 1.3BAlibaba · 1.3B	`FP16`	19.8 GB	14.5 min	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 13.8/15	CogVideoX 5BZhipu AI · 5.0B	`FP8`	14.3 GB	9.8 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 37.9/45, Memory fit 12.0/25, Speed 4.9/15, Memory use 15.0/15	LTX-2.3Lightricks · 18.9B	`FP8`	19.0 GB	28.3 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 10.6/15	CogVideoX 2BZhipu AI · 1.7B	`FP8`	11.0 GB	3.3 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 30.0/45, Memory fit 12.0/25, Speed 12.6/15, Memory use 15.0/15	LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0B	`FP8`	16.1 GB	4.2 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 15.0/15	SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4B	`FP8`	16.7 GB	16.3 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 6.9/15, Memory use 13.2/15	Wan 2.1 VACE 1.3BAlibaba · 2.2B	`FP8`	13.7 GB	14.2 min	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 36.2/45, Memory fit 12.0/25, Speed 4.9/15, Memory use 15.0/15	LTX-2 (19B, video + audio)Lightricks · 18.9B	`FP8`	19.0 GB	28.3 min	Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 25.6/45, Memory fit 18.0/25, Speed 6.9/15, Memory use 15.0/15	Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0B	`FP8`	22.0 GB	14.3 min	Tight fit
65 ptsGood (B) · 65 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 2.4/15, Memory use 15.0/15	Wan 2.2 I2V A14BAlibaba · 14.0B	`FP8`	23.3 GB	1.9 h	Tight fit
65 ptsGood (B) · 65 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 2.4/15, Memory use 15.0/15	Wan 2.2 T2V A14BAlibaba · 14.0B	`FP8`	23.3 GB	1.9 h	Tight fit
63 ptsGood (B) · 63 of 100 points: Model quality 27.3/45, Memory fit 18.0/25, Speed 3.3/15, Memory use 15.0/15	Mochi 1 Preview (10B)Genmo · 10.0B	`FP8`	21.9 GB	62.9 min	Tight fit
62 ptsGood (B) · 62 of 100 points: Model quality 33.3/45, Memory fit 12.0/25, Speed 2.5/15, Memory use 15.0/15	SkyReels V2 T2V 14B 540PSkywork · 14.0B	`FP16`	19.1 GB	1.8 h	Runs well
61 ptsGood (B) · 61 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 2.2/15, Memory use 15.0/15	Wan 2.1 I2V 14B 720PAlibaba · 14.0B	`FP8`	23.3 GB	2.4 h	Tight fit
61 ptsGood (B) · 61 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 2.2/15, Memory use 15.0/15	Wan 2.1 T2V 14BAlibaba · 14.0B	`FP8`	23.3 GB	2.4 h	Tight fit
60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15	AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3B	`FP16`	4.7 GB	73 s	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 31.5/45, Memory fit 12.0/25, Speed 1.7/15, Memory use 15.0/15	Open-Sora 2.0 (11B)HPC-AI Tech · 11.0B	`FP16`	19.3 GB	3.9 h	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 30.9/45, Memory fit 10.0/25, Speed 4.3/15, Memory use 15.0/15	Wan 2.2 TI2V 5BAlibaba · 5.0B	`FP8`	22.1 GB	36.8 min	Tight fit
59 ptsGood (B) · 59 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 1.9/15, Memory use 15.0/15	Wan 2.2 Animate 14BAlibaba · 17.3B	`Q4 GGUF`	21.3 GB	3.0 h	Tight fit
59 ptsGood (B) · 59 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 1.8/15, Memory use 15.0/15	Wan 2.1 VACE 14BAlibaba · 17.3B	`Q4 GGUF`	22.0 GB	3.5 h	Tight fit
11 ptsWon't run (F) · 11 of 100 points: Model quality 11.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	HunyuanVideo 1.5 (8.3B)Tencent · 8.3B	`FP8`	23.9 GB	—	Won't run
10 ptsWon't run (F) · 10 of 100 points: Model quality 10.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	SkyReels V2 T2V 14B 720PSkywork · 14.0B	`FP8`	26.0 GB	—	Won't run
10 ptsWon't run (F) · 10 of 100 points: Model quality 10.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Step-Video T2V (30B)StepFun · 30.0B	`FP8`	25.0 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0B	`FP8`	24.7 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	HunyuanVideo 13BTencent · 13.0B	`Q4 GGUF`	24.8 GB	—	Won't run
9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	HunyuanVideo I2V 13BTencent · 13.0B	`Q4 GGUF`	24.8 GB	—	Won't run
8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0B	`FP16`	29.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	CogVideoX 1.5 5BZhipu AI · 5.6B	`FP8`	31.2 GB	—	Won't run
7 ptsWon't run (F) · 7 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Allegro (2.8B)Rhymes AI · 2.8B	`FP16`	24.7 GB	—	Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 405 of 536 LLMs run well on your AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB).

Cheapest upgrade Intel Arc Pro B70 32.0 GB · $949 launch price +7 LLMs run well, including Llama 3.3 Nemotron Super 49B v1.5

Best value AMD Radeon PRO W7800 48GB 48.0 GB · $2,799 launch price +38 LLMs run well, including Qwen3 Coder Next (80B-A3B)

Biggest jump NVIDIA RTX PRO 6000 Blackwell 96.0 GB · $8,565 launch price +60 LLMs run well, including Qwen3.8 Flash Next (125B-A6B)

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.