Mistral AI logo

Devstral Small 2

Mistral AIOpen WeightsPending Human Review

Devstral Small 2 is the local deployment tier of Mistral’s second-generation coding family. The 24B dense model combines repository-level coding, tool interaction, and image input, allowing screenshots and visual requirements to inform software changes. Apache-2.0 weights enable private customization and self-hosting. It shares the large model’s 256K context capacity, but its smaller size trades difficult-task capability for lower memory and inference cost. Tool execution is provided by a coding scaffold such as Mistral Vibe.

2025-12-09
24B
Dense Transformer with vision encoder
Apache-2.0

Specifications

Parameters
24B
Architecture
Dense Transformer with vision encoder
License
Apache-2.0
Context Window
262,144 tokens
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Devstral
API Access
Available
Chat Interface
Not Available

Capabilities & Limitations

Capabilities
agentic codingvisiontool usemulti-file editing
Known Limitations
Smaller tier is weaker on difficult repository tasksLong contexts increase runtime memory requirements
Notable Use Cases
local coding assistantsscreenshot-to-codeprivate repository automation
Tool Use Support
Yes

Related Models