bf16 Open on Hugging Face
Parameters
30B
Weights (est.)
≈ 61.0 GB
Mac memory (est.)
96 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/North-Mini-Code-1.0-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- CohereLabs/North-Mini-Code-1.0 (finetune) · North Mini Code 1.0 on the radar →
- Vendor
- Cohere
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 171 in the last 30 days · 1.3K all time · 3 likes
- Published
- 2026-06-09 · updated 2026-06-09 (5mo ago)
- Tags
- cohere2_moe, chat, code, agent
Other MLX builds of CohereLabs/North-Mini-Code-1.0
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| North-Mini-Code-1.0-4bit | 4-bit | ≈ 18.5 GB | 24 GB+ | 713 |
| North-Mini-Code-1.0-5bit | 5-bit | ≈ 22.2 GB | 32 GB+ | 62 |
| North-Mini-Code-1.0-6bit | 6-bit | ≈ 25.9 GB | 32 GB+ | 102 |
| North-Mini-Code-1.0-bf16 (this one) | bf16 | ≈ 61.0 GB | 96 GB+ | 171 |