Devstral Small 2 24B Instruct needs ~30.8 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~253 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
272.4 tok/s
TTFT
711 ms
Safe context
256K
Memory
30.8 GB / 128.0 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 | S | Runs well | 272.4 tok/s | 388 ms | 256K |
| Coding | S | Runs well | 253.4 tok/s | 764 ms | 256K |
| Agentic Coding | S | Runs well | 272.4 tok/s | 1034 ms | 256K |
| Reasoning | S | Runs well | 272.4 tok/s | 840 ms | 256K |
| RAG | S | Runs well | 272.4 tok/s | 1292 ms | 256K |
How Devstral Small 2 24B Instruct (24B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | A80 |
Q3_K_S | 3 | 11.8 GB | Low | A80 |
NVFP4 | 4 |
Copy-paste commands to run Devstral Small 2 24B Instruct on your machine.
Run
ollama run devstral-small-2Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 53.8 tok/s | ||
| 30.5B | S |
Yes, AMD Instinct MI300A 128GB can run Devstral Small 2 24B Instruct with a S grade (Runs well). Expected decode speed: 253.4 tok/s.
Devstral Small 2 24B Instruct (24B parameters) requires approximately 30.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Devstral Small 2 24B Instruct is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI300A 128GB, Devstral Small 2 24B Instruct achieves approximately 253.4 tokens per second decode speed with a time-to-first-token of 764ms using Q4_K_M quantization.
For coding workloads, Devstral Small 2 24B Instruct on AMD Instinct MI300A 128GB receives a S grade with 253.4 tok/s and 256K context.
On AMD Instinct MI300A 128GB, Devstral Small 2 24B Instruct can safely use up to 256K tokens of context. The model's official context limit is 256K, 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/devstral-small-2-24b-on-instinct-mi300a-128gb" 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 |
| A80 |
Q4_K_M | 4 | 14.6 GB | Medium | A80 |
Q5_K_M | 5 | 17.3 GB | High | A80 |
Q6_K | 6 | 19.7 GB | High | A80 |
Q8_0 | 8 | 25.7 GB | Very High | A81 |
F16Best for your GPU | 16 | 49.2 GB | Maximum | A85 |
| 561 tok/s |
| 27B | S | 243.3 tok/s |
| 27B | S | 151.7 tok/s |
| 122B | S | 149.2 tok/s |