With 20 GB of VRAM, the RX 7900 XT runs Mistral Small 3.2 24B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 16.2 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 16.2 GB and fits in the 19.4 GB available, with 3.2 GB to spare.
~16.2 GB (15.6 GB–16.9 GB) needed · estimate
Fits entirely in VRAM · 3.2 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~26.7 GB · 2.5–5 tok/s estimate | CPU/GPU offload |
|---|---|
| Mistral Small 3.2 24B Instruct Q6_K8K~21.1 GB · 8–15 tok/s estimate | CPU/GPU offload |
| Mistral Small 3.2 24B Instruct Q5_K_M8K~18.6 GB · 29–41 tok/s estimate | Compatible |
| Mistral Small 3.2 24B Instruct Q4_K_M8K~16.2 GB · 33–47 tok/s estimate | Excellent |
| Mistral Small 3.2 24B Instruct IQ4_XS8K~14.7 GB · 36–52 tok/s estimate | Excellent |
| Mistral Small 3.2 24B Instruct Q3_K_M8K~13.4 GB · 39–57 tok/s estimate | Excellent |
Prices and links follow the market you choose.
20 GB GDDR6 · 800 GB/s · 315 W
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.
