GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Devstral Small 2

AI model Released Dec 9, 2025

Context window: 262,144 tokens
Maximum output: 262,144 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Devstral Small 2

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Context window: 262,144 tokens
Maximum output: 262,144 tokens
Reasoning: No
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2025-12
Model license: Apache-2.0

Input modalities

text
image

Output modalities

text