Will this model run on your hardware?
Can I run Cohere: North Mini Code locally?
- 30B parameters (3.3B active, MoE)
- context up to 488K
- licence: apache-2.0
- Weights: CohereLabs/North-Mini-Code-1.0 · GGUF: unsloth/North-Mini-Code-1.0-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 32.4 GB |
| UD-Q6_K | 25.5 GB |
| UD-Q5_K_M | 22.9 GB |
| UD-Q4_K_M | 19.2 GB |
| MXFP4 | 18.7 GB |
| UD-Q3_K_M | 14.2 GB |
Run it locally
ollama run hf.co/unsloth/North-Mini-Code-1.0-GGUF:UD-Q4_K_M
llama serve -hf unsloth/North-Mini-Code-1.0-GGUF:UD-Q4_K_M
LM Studio: open unsloth/North-Mini-Code-1.0-GGUF