← Catalog
Mistral Small 3
AvailableMistral AIOpen source
A latency-optimized 24B dense model under Apache-2.0 — a popular local-deployment workhorse.
Specifications
- License
- Open source · Apache-2.0
- Weights
- Downloadable
- Architecture
- Dense
- Parameters
- 24B
- Context window
- 32K tokens
- Max output
- 16K tokens
- Knowledge cutoff
- Oct 31, 2024
- Price (in / out, $/M)
- —
- Modalities
- TextCode
Benchmarks
No benchmark scores recorded yet. Spotted some? Submit a correction.
Vendor-reported figures are claims until independently verified. See methodology.