With 48 GB of VRAM, the RTX 6000 Ada runs Qwen2.5 Coder 32B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 22.4 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 22.4 GB and fits in the 46.6 GB available, with 24.2 GB to spare.
~22.4 GB (21.6 GB–23.2 GB) needed · estimate
Fits entirely in VRAM · 24.2 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen2.5 Coder 32B Instruct Q8_08K~37 GB · 19–26 tok/s estimate | Excellent |
|---|---|
| Qwen2.5 Coder 32B Instruct Q6_K8K~29.3 GB · 24–33 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B Instruct Q5_K_M8K~25.7 GB · 27–37 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B Instruct Q4_K_M8K~22.4 GB · 31–43 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B Instruct IQ4_XS8K~20.3 GB · 34–47 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B Instruct Q3_K_M8K~18.5 GB · 37–52 tok/s estimate | Excellent |
Prices and links follow the market you choose.
48 GB GDDR6 ECC · 960 GB/s · 300 W
ExcellentRuns Qwen2.5 Coder 32B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
