All tasks / Models
Mistral Small 4 (2603)
Mistral's open-weights Small line (Apache-2.0); Small 4 is a 119B MoE with 6.5B active parameters.
- Mistral AI
- Open weights
- Released Mar 2026
Where it ranks
- CChat & assistantsModels · Local · 11 on Artificial Analysis Intelligence Index (secondary benchmark)
- CCodingModels · Local · 11 on Artificial Analysis Intelligence Index (secondary benchmark)
Facts
- Vendor
- Mistral AI
- Family
- Mistral Small
- Released
- Mar 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 119B (6.5B active)
- GPU memory to run locally
- ~69 GB (4-bit ≈ 119 B × 0.57 GB + 1.5 GB ≈ 69 GB, estimate.)
- API price
- $0.15 in / $0.6 out per 1M tokens (OpenRouter listed price)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from openrouter.ai, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 11 | Mistral Small 4 (Reasoning)Raw value from the page's embedded model data; the site displays it rounded to an integer. | 19 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.
Earlier versions
- Mistral Small 3.2 (2506) · Jun 2025