The model scored 33.4 on the Artificial Analysis Coding Index.
We made a small coding model. Its open source apache 2.0. Now more than ever i think this tech needs to be built in public so that those using it are in control. Try it out if you want a small and efficient coding model.
Users praised Cohere's open-source North Mini Code model for its small efficient size, Apache 2.0 licensing, and community benefits, while one criticized the launch video for repeatedly showing failed tools.
Introducing Cohere's first open-source coding model: North Mini Code
Small & efficient, designed for agentic performance and built for community input.
We encourage developers to share their builds with us and give feedback to shape future iterations. Let’s shape the future of sovereign AI together.
Download: https://huggingface.co/CohereLabs/North-Mini-Code-1.0
Cohere just released North Mini Code, a small 30B parameter (3B active) open weights coding model that scores 27.6 on the Artificial Analysis Intelligence Index
Less than a month since @cohere's last model release, Command A+, has launched another open weights model that is optimized for coding, and much smaller at 30B total parameters and 3B active parameters.
Key Takeaways:
➤ Achieves 27.6 on the Artificial Analysis Intelligence Index, above gpt-oss-20B (high) at 24.5 and just below Mistral Small 4 (119B parameters, 6.5B active) at 27.8
➤ Scores competitively on the Artificial Analysis Coding Index (weighted average of Terminal-Bench Hard and SciCode) against open weights models in its size class, scoring 33.4, significantly above GLM-4.7-Flash at 25.9, and below Qwen3.6 35B A3B at 35.2. However, it underperforms on non-coding agentic tasks, scoring 14% on GDPval-AA and 37% on 𝜏²-Bench Telecom
➤ On Cohere’s API, North Mini Code is faster than several comparable open weights models of its intelligence and size class (~199 output tokens per second)
➤ North Mini Code is a text-only 30B total parameter and 3B active parameter model, and is open-sourced under the Apache 2.0 license
Small: 30 billion parameters, 3B active.
Efficient: Benchmarks to 33.4 on the Artificial Analysis Coding Index, competitive among similar sized models.
Open Source: Apache 2.0 license so developers can experiment, test, and build their way.
Learn more: https://cohere.com/blog/north-mini-code
We open-sourced a feisty small agentic coding model.
- 30B total, 3B active - 256K total context - Compatible with @opencode - Apache 2.0. Weights on @huggingface
Introducing Cohere's first open-source coding model: North Mini Code
Small & efficient, designed for agentic performance and built for community input.
this model is the opposite of mythos.
Its small, cost effective, apache 2.0, and locally deployable. This is the way LLMs should go.
small, open source, transparent and sovereign vs large, expensive, proprietary and hegemonic
Introducing Cohere's first open-source coding model: North Mini Code
Small & efficient, designed for agentic performance and built for community input.
North Mini Code scores 14% on GDPval-AA and 37% on 𝜏²-Bench Telecom, resulting in an overall weighted score of 21.7 on the Artificial Analysis Agentic Index
North Mini Code uses more output tokens to complete the Artificial Analysis Intelligence Index evaluations suite than most comparable models of its size and intelligence
Full intelligence evaluations breakdown below:
@nickfrosst More info:
In our pre-release speed testing, North Mini Code performed above several comparable open weights models of its intelligence and size class (~199 output tokens per second)
@cohere Wow! This is another cool release!
See Artificial Analysis for further details and benchmarks: https://artificialanalysis.ai/models/north-mini-code
@cohere congrats! https://huggingface.co/blog/CohereLabs/introducing-north-mini-code
@cohere 30B total / 3B active is a wild MoE config. Speed of a 3B model, but you still need the VRAM of a 30B to hold all 128 experts. Local VRAM is the real bottleneck here, but the TPS should be ridiculous.
codehere
Introducing Cohere's first open-source coding model: North Mini Code
Small & efficient, designed for agentic performance and built for community input.
@cohere codehere
@cohere Did you literally just post a six-minute launch video where it fails edit tool calls for half of the video?
@cohere nice to see another moe at 30b/3b form factor. apache 2.0 is the real win. would love to see how agentic coding shakes out vs qwen3 on the same hardware, that 33.4 benchmark number only tells part of the story
@cohere @DJLougen you’re up 😈
The model scored 33.4 on the Artificial Analysis Coding Index.
We made a small coding model. Its open source apache 2.0. Now more than ever i think this tech needs to be built in public so that those using it are in control. Try it out if you want a small and efficient coding model.
