Downloads · 30 days
158
7% of all-time downloads
North-Mini-Code-1.0-MLX-MXFP4
bsisduck/North-Mini-Code-1.0-MLX-MXFP4
North-Mini-Code-1.0-MLX-MXFP4 is a text generation model from bsisduck. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
MXFP4 MLX conversion of CohereLabs/North-Mini-Code-1.0.
All-time downloads
2.3K
Public
Parameters
30.5B
17.6 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors17.6 GB · 100%
Parameter types
How the weights are stored.
U3229.5B · 97%
Try a prompt
Base models
Model card
From the Hugging Face model README
North-Mini-Code-1.0 MLX MXFP4
MXFP4 MLX conversion of CohereLabs/North-Mini-Code-1.0.
- Source revision:
effaeda477c041c107d5a3d8c599cb5d6c5878ef - Architecture:
Cohere2MoeForCausalLM/cohere2_moe - Quantization: MLX
mxfp4, group size 32, 4 bits - Artifact size: 17.59 GB, 4 safetensor shards
- Verification: conversion completed, headers readable, smoke test passed
- Benchmark on M2 Max 32 GB: 218.449 prompt tok/s, 42.385 generation tok/s, 17.788 GB peak memory
Requires pinned experimental MLX-LM cohere2_moe support until it lands in a release:
pip install "mlx-lm @ git+https://github.com/Terrencezzj/mlx-lm.git@f43507c5c30bdebdb92d308ac11aa8f96b418c2e"
- Task
- Text Generation
- Library
- mlx
- Type
- cohere2_moe
- License
- apache-2.0
- Languages
- en
- Created
- Jun 9, 2026
- Updated
- Jun 9, 2026