Head to head
Devstral Small 2 24B vs Qwen 2.5 Coder 32B
Side-by-side specs, benchmarks, and a verdict by use case.
| Spec | Devstral Small 2 24B | Qwen 2.5 Coder 32B |
|---|---|---|
| Parameters | 24B | 32B |
| Author | Mistral AI | Alibaba |
| License | Apache 2.0 | Apache 2.0 |
| Context window | 0k | 0k |
| VRAM at Q4 | 14 GB | 19 GB |
| VRAM at Q5 | 17 GB | 23 GB |
| VRAM at Q8 | 26 GB | 35 GB |
| VRAM at FP16 | 48 GB | 64 GB |
| Use cases | code, fr | code |
Verdict
Both models sit in a similar size class. The pick depends on tags, license, and benchmarks rather than raw parameter count.