Cohere
Cohere's open-weight 30B total and 3B active mixture-of-experts model for agentic software engineering, terminal agents, and local coding workflows.
Running this yourself: can likely run on your own machine.
48.6
Quality Score
---
Arena ELO
Unknown
Parameters
500K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
23.6K
Downloads
549
Likes
Jun 2026
Released
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
CohereLabs/North-Mini-Code-1.0 · Hugging Face
Cohere published benchmark or leaderboard evidence for North-Mini-Code-1.0.
View sourceCohereLabs/North-Mini-Code-1.0-fp8 · Hugging Face
Cohere published benchmark or leaderboard evidence for North-Mini-Code-1.0-fp8.
View sourceCohereLabs/North-Mini-Code-1.0-w4a16 · Hugging Face
Cohere published benchmark or leaderboard evidence for North-Mini-Code-1.0-w4a16.
View sourceCohereLabs/North-Mini-Code-1.0 · Hugging Face
Cohere published benchmark or leaderboard evidence for BLS-Mini-Code-1.0.
View source