With 80 GB of VRAM, the H100 PCIe runs Qwen2.5 72B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 46.6 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 46.6 GB and fits in the 77.6 GB available, with 31 GB to spare.
~46.6 GB (45.3 GB–47.9 GB) needed · estimate
Fits entirely in VRAM · 31 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 72B Instruct Q8_08K~79.3 GB · 6.5–12 tok/s estimate | CPU/GPU offload |
|---|---|
| Qwen2.5 72B Instruct Q6_K8K~62.1 GB · 23–31 tok/s estimate | Excellent |
| Qwen2.5 72B Instruct Q5_K_M8K~54.1 GB · 26–35 tok/s estimate | Excellent |
| Qwen2.5 72B Instruct Q4_K_M8K~46.6 GB · 29–41 tok/s estimate | Excellent |
| Qwen2.5 72B Instruct IQ4_XS8K~42.4 GB · 32–45 tok/s estimate | Excellent |
| Qwen2.5 72B Instruct Q3_K_M8K~38.2 GB · 35–49 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.
