GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Devstral Small

AI model Released Jul 10, 2025

Context window: 128,000 tokens
Maximum output: 128,000 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Devstral Small

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Context window: 128,000 tokens
Maximum output: 128,000 tokens
Reasoning: No
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2025-05

Input modalities

text

Output modalities

text