Mistral Small 3.1 24B needs ~37.2 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~282 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
303.6 tok/s
TTFT
638 ms
Safe context
131K
Memory
37.2 GB / 192.0 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 | 282.4 tok/s | 374 ms | 131K |
| Coding | A | Runs well | 282.4 tok/s | 686 ms | 131K |
| Agentic Coding | A | Runs well | 282.4 tok/s | 997 ms | 131K |
| Reasoning | A | Runs well | 282.4 tok/s | 810 ms | 131K |
| RAG | A | Runs well | 282.4 tok/s | 1247 ms | 131K |
How Mistral Small 3.1 24B (24B params) fits at each quantization level on AMD Instinct MI300X 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | B68 |
Q3_K_S | 3 | 11.8 GB | Low | B68 |
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 | 59.9 tok/s | ||
| 30.5B | S |
Yes, AMD Instinct MI300X 192GB can run Mistral Small 3.1 24B with a A grade (Runs well). Expected decode speed: 282.4 tok/s.
Mistral Small 3.1 24B (24B parameters) requires approximately 37.2 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 AMD Instinct MI300X 192GB, Mistral Small 3.1 24B achieves approximately 282.4 tokens per second decode speed with a time-to-first-token of 686ms using Q4_K_M quantization.
For coding workloads, Mistral Small 3.1 24B on AMD Instinct MI300X 192GB receives a A grade with 282.4 tok/s and 131K context.
On AMD Instinct MI300X 192GB, 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-instinct-mi300x-192gb" 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 |
| B68 |
Q4_K_M | 4 | 14.6 GB | Medium | B68 |
Q5_K_M | 5 | 17.3 GB | High | B68 |
Q6_K | 6 | 19.7 GB | High | B69 |
Q8_0 | 8 | 25.7 GB | Very High | B69 |
F16Best for your GPU | 16 | 49.2 GB | Maximum | A72 |
| 625.1 tok/s |
| 27B | S | 271.1 tok/s |
| 27B | S | 169 tok/s |
| 122B | S | 166.2 tok/s |