With 48 GB of VRAM, the Radeon PRO W7900 runs Qwen3 Coder 30B-A3B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 19.8 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 19.8 GB and fits in the 46.6 GB available, with 26.8 GB to spare.
~19.8 GB (19.1 GB–20.5 GB) needed · estimate
Fits entirely in VRAM · 26.8 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen3 Coder 30B-A3B Instruct Q8_08K~33.4 GB · 62–106 tok/s estimate | Excellent |
|---|---|
| Qwen3 Coder 30B-A3B Instruct Q6_K8K~26.2 GB · 69–123 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B Instruct Q5_K_M8K~22.9 GB · 73–132 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B Instruct Q4_K_M8K~19.8 GB · 78–141 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B Instruct IQ4_XS8K~17.7 GB · 81–149 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B Instruct Q3_K_M8K~16 GB · 83–155 tok/s estimate | Excellent |
Prices and links follow the market you choose.
48 GB GDDR6 ECC · 864 GB/s · 295 W
ExcellentRuns Qwen3 Coder 30B-A3B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
