Mistral Small 3.1 24B needs ~27.9 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~99 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
98.5 tok/s
TTFT
1965 ms
Safe context
131K
Memory
27.9 GB / 96.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 98.5 tok/s | 1072 ms | 131K |
| Coding | A | Runs well | 98.5 tok/s | 1965 ms | 131K |
| Agentic Coding | A | Runs well | 91.6 tok/s | 3073 ms | 131K |
| Reasoning | A | Runs well | 98.5 tok/s | 2323 ms | 131K |
| RAG | A | Runs well | 98.5 tok/s | 3573 ms | 131K |
How Mistral Small 3.1 24B (24B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | A71 |
Q3_K_S | 3 | 11.8 GB | Low | A71 |
NVFP4 | 4 |
Copy-paste commands to run Mistral Small 3.1 24B on your machine.
Run
ollama run mistral-small:24bYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 19.4 tok/s | ||
| 30.5B |
Yes, RTX PRO 6000 Blackwell Server Edition 96GB can run Mistral Small 3.1 24B with a A grade (Runs well). Expected decode speed: 98.5 tok/s.
Mistral Small 3.1 24B (24B parameters) requires approximately 27.9 GB of memory with Q4_K_M quantization.
The recommended quantization for Mistral Small 3.1 24B is Q4_K_M, which balances quality and memory efficiency.
On RTX PRO 6000 Blackwell Server Edition 96GB, Mistral Small 3.1 24B achieves approximately 98.5 tokens per second decode speed with a time-to-first-token of 1965ms using Q4_K_M quantization.
For coding workloads, Mistral Small 3.1 24B on RTX PRO 6000 Blackwell Server Edition 96GB receives a A grade with 98.5 tok/s and 131K context.
On RTX PRO 6000 Blackwell Server Edition 96GB, Mistral Small 3.1 24B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mistral-small-3.1-24b-on-rtx-pro-6000-blackwell-server-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
13.4 GB |
| Medium |
| A71 |
Q4_K_M | 4 | 14.6 GB | Medium | A71 |
Q5_K_M | 5 | 17.3 GB | High | A71 |
Q6_K | 6 | 19.7 GB | High | A72 |
Q8_0 | 8 | 25.7 GB | Very High | A73 |
F16Best for your GPU | 16 | 49.2 GB | Maximum | A78 |
| 202.8 tok/s |
| 27B | S | 88 tok/s |
| 27B | S | 88.2 tok/s |
| 122B | S | 53.9 tok/s |