With 96 GB of VRAM, the RTX PRO 6000 Blackwell runs Mistral 7B Instruct v0.3 at Q4_K_M entirely on the GPU with an 8K context (about 5.9 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 5.9 GB and fits in the 93.1 GB available, with 87.2 GB to spare.
~5.9 GB (5.6 GB–6.3 GB) needed · estimate
Fits entirely in VRAM · 87.2 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Mistral 7B Instruct v0.3 Q8_08K~9.2 GB · 127–189 tok/s estimate | Excellent |
|---|---|
| Mistral 7B Instruct v0.3 Q6_K8K~7.5 GB · 152–232 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3 Q5_K_M8K~6.7 GB · 166–260 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3 Q4_K_M8K~5.9 GB · 183–293 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3 IQ4_XS8K~5.5 GB · 195–317 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3 Q3_K_M8K~5.2 GB · 206–341 tok/s estimate | Excellent |
Prices and links follow the market you choose.
96 GB GDDR7 ECC · 1,792 GB/s · 600 W
ExcellentRuns Mistral 7B Instruct v0.3 Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
