Hardware · Clusters

What your 2 devices can run together

Add the computers, Macs, mini PCs and boards you own, and how they’re connected. We work out which models they can run together, how fast, and which free tool to use.

Device 1
Device 2
Device 3

48.0 GBusable memory together (the largest device has 24.0 GB)

32models only the cluster can run

111run better or faster than on any one device

311B (15.0B active)biggest model it adds: MiMo V2.6 Flash (310B-A15B)

Connected by 2.5 Gb Ethernet. The wait for the first word is worked out for a 1,000-token prompt (a short chat).

The devices

Tool to use

llama.cpp RPC best estimate for 138 of the 143 models the cluster adds

Mixed devices you already own, a Mac, a gaming PC, a mini PC or a Jetson, when one GGUF model won't fit on any of them alone.

ggml-rpc-server --host 0.0.0.0 --port 50052 -c   # on each worker
llama-server -hf <model-GGUF> -ngl 99 --rpc 192.168.1.10:50052,192.168.1.11:50052   # on the main machine

550 LLMs your devices can run

Models the cluster adds come first, best match first, then the ones a single device already runs as well. Filter vs one device to pick. Speeds are estimates for one person chatting.

Quality Model Quant Memory Speed Runs Devices Tool vs one device
91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active) Q4_K_M 114 GB 16.9 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 120BOpenAI · 117B (5.1B active) MXFP4 70.5 GB 28.2 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B)StepFun · 201B (11.0B active) Q4_K_M 127 GB 9.7 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active) Q4_K_M 126 GB 9.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active) Q3_K_M 118 GB 13.7 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active) Q3_K_M 118 GB 13.7 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active) Q3_K_M 118 GB 13.7 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
74Great quality (A) · 74 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active) Q3_K_M 118 GB 13.7 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active) Q3_K_M 120 GB 6.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active) Q3_K_M 120 GB 6.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
74Great quality (A) · 74 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Qwen3-VL 235B-A22B InstructAlibaba · 236B (22.0B active) Q3_K_M 121 GB 6.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. dots.llm1 Instructrednote · 143B (14.0B active) Q4_K_M 99.0 GB 9.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 235B-A22BAlibaba · 235B (22.0B active) Q3_K_M 120 GB 6.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active) Q3_K_M 120 GB 6.5 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Command A+ (218B-A25B)Cohere · 219B (25.0B active) Q3_K_M 111 GB 6.3 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B)Thinking Machines Lab · 266B (12.0B active) Q2_K 110 GB 14.9 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active) Q2_K 128 GB 11.5 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active) Q2_K 126 GB 13.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active) Q3_K_M 123 GB 5.4 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
70Great quality (A) · 70 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Baichuan M3 235B-A22BBaichuan · 235B (22.0B active) Q3_K_M 120 GB 6.8 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B)Xiaomi · 311B (15.0B active) Q2_K 128 GB 11.5 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active) Q2_K 120 GB 13.4 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active) Q2_K 126 GB 8.6 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active) Q2_K 128 GB 11.5 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek Coder V2 (236B)DeepSeek · 236B (21.0B active) Q3_K_M 120 GB 7.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active) Q3_K_M 120 GB 7.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V2.5 1210DeepSeek · 236B (21.0B active) Q3_K_M 120 GB 7.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V2.5DeepSeek · 236B (21.0B active) Q3_K_M 120 GB 7.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active) Q2_K 126 GB 4.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V2 ChatDeepSeek · 236B (21.0B active) Q3_K_M 120 GB 7.1 tok/s Slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 253B Q2_K 109 GB 0.9 tok/s Very slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 35/100 (quality, fit, speed and memory use) sets the ranking. Falcon 180B ChatTII · 180B Q4_K_M 113 GB 0.7 tok/s Very slowheavy RAM offload NVIDIA PC 1 (card + RAM) + NVIDIA PC 2 (card + RAM)Pipeline split llama.cpp RPC Needs the clusterWon’t run on any one of them
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle · 26B (3.8B active) Q8_0 31.4 GB 47.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 124 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active) Q6_K 32.6 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active) Q6_K 32.6 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active) Q8_0 40.5 GB 50.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B)Recursive · 40B (2.5B active) Q6_K 36.5 GB 58.1 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 208 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 31BGoogle · 31B Q6_K 30.9 GB 37.8 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Tensor split MLX distributed Better on the clusterAlone: Runs well on NVIDIA PC 1, 39.6 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active) Q6_K 33.2 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active) Q8_0 37.1 GB 50.4 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active) Q8_0 34.2 GB 71.8 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Tensor split MLX distributed Better on the clusterAlone: Runs great on NVIDIA PC 1, 146 tok/s
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active) Q8_0 40.5 GB 50.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
86Excellent quality (A+) · 86 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Agents-A1 35B-A3BInternScience · 35B (3.0B active) Q6_K 32.6 GB 56.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 173 tok/s
85Excellent quality (A+) · 85 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy-Memory 30B-A3BTencent · 30B (3.0B active) Q8_0 36.3 GB 50.4 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Pipeline split llama.cpp RPC Better on the clusterAlone: Runs well on NVIDIA PC 1, 155 tok/s
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. TMax 27BAi2 · 27B Q6_K 26.6 GB 39.2 tok/s Runs great NVIDIA PC 1 + NVIDIA PC 2Tensor split MLX distributed Better on the clusterAlone: Runs great on NVIDIA PC 1, 45.2 tok/s

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.

Was this page helpful?