Devstral Small 2 24B Instruct needs ~21.2 GB VRAM. Radeon Pro W7800 32GB has 32.0 GB. With Q4_K_M quantization, expect ~25 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
25.0 tok/s
TTFT
7758 ms
Safe context
87K
Memory
21.2 GB / 32.0 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 | 25.0 tok/s | 4232 ms | 87K |
| Coding | S | Runs well | 25.0 tok/s | 7758 ms | 87K |
| Agentic Coding | S | Runs well | 25.0 tok/s | 11285 ms | 87K |
| Reasoning | S | Runs well | 25.0 tok/s | 9169 ms | 87K |
| RAG | S | Runs well | 25.0 tok/s | 14106 ms | 87K |
Inference speed
Estimated decode speed (tokens/sec) for Devstral Small 2 24B Instruct at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~88 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 88.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 56.3 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 50.8 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 48.1 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 40.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 36.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 36.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 34.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 32.3 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 21.3 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 17.6 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 16.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 7.5 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 4.7 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.2 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Devstral Small 2 24B Instruct (24B params) fits at each quantization level on Radeon Pro W7800 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | S87 |
Q3_K_S | 3 | 11.8 GB | Low | S88 |
NVFP4 | 4 | 13.4 GB | Medium | S89 |
Q4_K_M | 4 | 14.6 GB | Medium | S90 |
Q5_K_M | 5 | 17.3 GB | High | S91 |
Q6_K | 6 | 19.7 GB | High | S90 |
Q8_0Best for your GPU | 8 | 25.7 GB | Very High | S90 |
F16 | 16 | 49.2 GB | Maximum | F0 |
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 |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 51.4 tok/s | |
| Qwen 3.5 27B | 27B | S | 22.3 tok/s | |
| Qwen 3.6 27B | 27B | S | 16.9 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 43.2 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 53.1 tok/s |
Yes, Radeon Pro W7800 32GB can run Devstral Small 2 24B Instruct with a S grade (Runs well). Expected decode speed: 25.0 tok/s.
Devstral Small 2 24B Instruct (24B parameters) requires approximately 21.2 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 Radeon Pro W7800 32GB, Devstral Small 2 24B Instruct achieves approximately 25.0 tokens per second decode speed with a time-to-first-token of 7758ms using Q4_K_M quantization.
For coding workloads, Devstral Small 2 24B Instruct on Radeon Pro W7800 32GB receives a S grade with 25.0 tok/s and 87K context.
On Radeon Pro W7800 32GB, Devstral Small 2 24B Instruct can safely use up to 87K 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-radeon-pro-w7800-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: