Qwen2.5 72B Instruct at Q4_K_M needs about 46.6 GB, more than the 48 GB of the RTX 6000 Ada: part of the model runs from system RAM, which slows generation. At Q3_K_M it fits entirely.
Q4_K_M · 8K context
The model needs about 46.6 GB but only 46.6 GB of VRAM is usable: 0 GB must be loaded into system RAM. It runs, 100% on the GPU, but more slowly.
~46.6 GB (45.3 GB–47.9 GB) needed · estimate
0 GB must be offloaded to system RAM
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen2.5 72B Instruct Q8_08K~79.3 GB · 0.6–1.1 tok/s estimate | Not recommended |
|---|---|
| Qwen2.5 72B Instruct Q6_K8K~62.1 GB · 1.2–2 tok/s estimate | Possible but slow |
| Qwen2.5 72B Instruct Q5_K_M8K~54.1 GB · 2–4 tok/s estimate | Possible but slow |
| Qwen2.5 72B Instruct Q4_K_M8K~46.6 GB · 12–20 tok/s estimate | CPU/GPU offload |
| Qwen2.5 72B Instruct IQ4_XS8K~42.4 GB · 17–22 tok/s estimate | Compatible |
| Qwen2.5 72B Instruct Q3_K_M8K~38.2 GB · 19–25 tok/s estimate | Excellent |
Prices and links follow the market you choose.
AMD
CompatibleRuns Qwen2.5 72B Instruct Q4_K_M entirely in memory
Unified memory PC
CompatibleRuns Qwen2.5 72B Instruct Q4_K_M entirely in memory
Lowest memory tier
ExcellentRuns Qwen2.5 72B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
