Devstral Small 2 24B
Apache 2.0Mistral AI · 24B · Dense
Coding-focused model with 256K context — 68% SWE-bench
Use Cases
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 8.2 GB | low | — |
| Q3_K_M | 3 | 11.3 GB | moderate | — |
| Q4_K_M | 4 | 12.8 GB | good | — |
| Q5_K_M | 5 | 15.9 GB | good | — |
| Q6_K | 6 | 18.9 GB | excellent | — |
| Q8_0 | 8 | 25.1 GB | excellent | — |
| F16 | 16 | 49.7 GB | lossless | — |
GPUs that run Devstral Small 2 24B
Devstral Small 2 24B needs about 12.8 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 16 GB of VRAM or more (69 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 16 GB | RTX 5080 , RX 7800 XT , Arc A770 |
| 20 GB | RTX 4000 SFF Ada , RX 7900 XT , RTX 4000 Ada |
| 24 GB | RTX 4090 , RX 7900 XTX , RTX 3090 Ti |
| 32 GB | RTX 5090 |
About this model
Note: this model requires Ollama 0.13.3 or later. Download Ollama
Devstral Small 2
Devstral is an agentic LLM for software engineering tasks. Devstral 2 models excel at using tools to explore codebases, editing multiple files and power software engineering agents.
The model achieves remarkable performance on SWE-bench.
ollama run devstral-small-2
Key Features
The Devstral 2 Instruct model offers the following capabilities:
Agentic Coding: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
Improved Performance: Devstral 2 is a step-up compared to its predecessors.
Better Generalization: Generalises better to diverse prompts and coding environments.
Use Cases
AI Code Assistants, Agentic Coding, and Software Engineering Tasks. Leveraging advanced AI capabilities for complex tool integration and deep codebase understanding in coding environments.
Benchmark Results
| Model/Benchmark | Size (B Tokens) | SWE Bench Verified | SWE Bench Multilingual | Terminal Bench |
|---|---|---|---|---|
| Devstral 2 | 123 | 72.2% | 61.3% | 40.5% |
| Devstral Small 2 | 24 | 65.8% | 51.6% | 32.0% |
| DeepSeek v3.2 | 671 | 73.1% | 70.2% | 46.4% |
| Kimi K2 Thinking | 1000 | 71.3% | 61.1% | 35.7% |
| MiniMax M2 | 230 | 69.4% | 56.5% | 30.0% |
| GLM 4.6 | 455 | 68.0% | – | 40.5% |
| Qwen 3 Coder Plus | 480 | 69.6% | 54.7% | 37.5% |
| Gemini 3 Pro | – | 76.2% | – | 54.2% |
| Claude Sonnet 4.5 | – | 77.2% | 68.0% | 42.8% |
| GPT 5.1 Codex Max | – | 77.9% | – | 58.1% |
| GPT 5.1 Codex High | – | 73.7% | – | 52.8% |
License
Apache 2.0