What AI models can the AMD Radeon PRO W7900 run?

VRAM: 48.0 GB
Usable for models: 48.0 GB
Memory bandwidth: 864 GB/s
FP16 compute: 122.6 TFLOPS
Released: 2023
Launch price: $3,999

Specifications

Maker	AMD
Type	Workstation / datacenter graphics card
Video memory (VRAM)	48.0 GB
Usable for AI models	48.0 GB
Memory bandwidth	864 GB/s
FP16 compute	122.6 TFLOPS
Interface	PCIe 4.0
Released	2023
Launch price (US)	$3,999

2 products with the AMD Radeon PRO W7900

AMD Radeon PRO W7900AMD · Workstation card · 48 GB · from $3,999Maker’s page (opens in a new tab)
AMD Radeon PRO W7900 Dual SlotAMD · Workstation card · 48 GB · from $3,499Maker’s page (opens in a new tab)

Best LLMs for the AMD Radeon PRO W7900

Grade · points	Model	Quant	Memory	Speed	Fit
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.6 35B-A3BAlibaba	`Q6_K`	32.6 GB	106 tok/s	Runs well
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.5 35B-A3BAlibaba	`Q6_K`	32.6 GB	106 tok/s	Runs well
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15	Gemma 4 26B-A4BGoogle	`Q8_0`	30.8 GB	61.2 tok/s	Runs well
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.5 35B-A3BDeepReinforce	`Q6_K`	32.6 GB	106 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Apodex 1.1 Mini (35B-A3B)Apodex	`Q6_K`	32.6 GB	106 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.0 35B-A3BDeepReinforce	`Q6_K`	32.6 GB	106 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GLM-4.7 Flash (30B-A3B)Zhipu AI	`Q8_0`	36.5 GB	77.5 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Agents-A1 35B-A3BInternScience	`Q8_0`	40.4 GB	77.5 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen AgentWorld 35B-A3BAlibaba	`Q8_0`	39.9 GB	77.5 tok/s	Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Laguna XS 2.1 (33B-A3B)Poolside	`Q8_0`	39.8 GB	77.5 tok/s	Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Nemotron Cascade 2 30B-A3BNVIDIA	`Q8_0`	36.5 GB	66.4 tok/s	Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	North Mini Code 1.0 (30B-A3B)Cohere	`Q8_0`	35.6 GB	77.5 tok/s	Runs well

Best Image models for the AMD Radeon PRO W7900

Grade · points	Model	Precision	Memory	Time per output	Fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`FP16`	37.1 GB	2.0 s	Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 15.0/15	FLUX.1 Krea [dev]Black Forest Labs	`FP16`	36.4 GB	13 s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 15.0/15	FLUX.1 [dev]Black Forest Labs	`FP16`	36.4 GB	13 s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15	Z-Image TurboAlibaba (Tongyi)	`FP16`	22.7 GB	2.8 s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	HiDream-I1 FastHiDream.ai	`FP8`	33.7 GB	10 s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 15.0/15	HiDream-I1 DevHiDream.ai	`FP8`	33.7 GB	17 s	Runs well

Best Video models for the AMD Radeon PRO W7900

Grade · points	Model	Precision	Memory	Time per output	Fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 37.9/45, Memory fit 23.0/25, Speed 10.0/15, Memory use 15.0/15	LTX-2.3Lightricks	`FP8`	44.3 GB	6.7 min	Tight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.5/15	LTX-Video 13B 0.9.8 (distilled)Lightricks	`FP8`	30.1 GB	60 s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 36.2/45, Memory fit 23.0/25, Speed 10.0/15, Memory use 15.0/15	LTX-2 (19B, video + audio)Lightricks	`FP8`	44.3 GB	6.7 min	Tight fit
82 ptsGreat (A) · 82 of 100 points: Model quality 37.9/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Wan 2.2 I2V A14BAlibaba	`FP8`	38.3 GB	26.8 min	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 37.9/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15	Wan 2.2 T2V A14BAlibaba	`FP8`	38.3 GB	26.8 min	Runs well

Best LLMs by task on this hardware Open in Model Finder

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.