With 24 GB of VRAM, the Tesla P40 runs Mistral Small 3.2 24B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 16.1 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 16.1 GB and fits in the 23.3 GB available, with 7.1 GB to spare.
~16.1 GB (15.5 GB–16.8 GB) needed · estimate
Fits entirely in VRAM · 7.1 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Mistral Small 3.2 24B Instruct Q8_08K~26.6 GB · 3.5–6.5 tok/s estimate | CPU/GPU offload |
|---|---|
| Mistral Small 3.2 24B Instruct Q6_K8K~21 GB · 13–17 tok/s estimate | Compatible |
| Mistral Small 3.2 24B Instruct Q5_K_M8K~18.5 GB · 15–20 tok/s estimate | Excellent |
| Mistral Small 3.2 24B Instruct Q4_K_M8K~16.1 GB · 17–22 tok/s estimate | Excellent |
| Mistral Small 3.2 24B Instruct IQ4_XS8K~14.6 GB · 19–25 tok/s estimate | Excellent |
| Mistral Small 3.2 24B Instruct Q3_K_M8K~13.3 GB · 21–28 tok/s estimate | Excellent |
Prices and links follow the market you choose.
AMD
ExcellentRuns Mistral Small 3.2 24B Instruct Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Mistral Small 3.2 24B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
