Cohere launches North Mini Code, a 30B open-source coding model

Hugging Face Blog

North Mini Code has 30B total parameters (3B active) and uses a Mixture-of-Experts architecture with 128 experts, released under Apache 2.0. It achieves strong results on agentic coding benchmarks like Terminal-Bench and SWE-Bench, and runs on a single H100 GPU.

CohereCoding model

See 14 more sources

CohereLabs/North-Mini-Code-1.021 days agoCohereLabs

unsloth/North-Mini-Code-1.0-GGUF17 days agounsloth

CohereLabs/BLS-Mini-Code-1.022 days agoCohereLabs

North Mini Code and Agentic Coding Benchmarks13 days ago

We released North Mini Code, our first open-source coding model, just two days ago. We’re already...19 days agoCohere

Cohere just released North Mini Code, a small 30B parameter (3B active) open weights coding model...21 days agoArtificial Analysis

Introducing Cohere's first open-source coding model: North Mini Code Small & efficient,...21 days agoCohere

Introducing Cohere's first open-source coding model: North Mini Code. Small & efficient,...21 days agoCohere

Cohere open-sources a coding agent that runs on a single H10021 days ago

Cohere sold sovereign AI to enterprises, now it’s targeting developers with its first coding model15 days agoPaul Sawers

Meet ‘North Mini Code’: Cohere’s 30B Open-Weight Mixture-of-Experts Model With 3B Active Parameters for Agentic Coding19 days agoAsif Razzaq

Updates on North Mini Code: 4 bit quant + Ollama + OpenRouter12 days agonick_frosstDiscuss

Cohere's First Model for Developers15 days agohmokiguessDiscuss

Command A Plus GGUFs posted15 days agocoder543Discuss

Hugging Face Blog

Jun 9, 3:56 PM