Instructions to use bsisduck/North-Mini-Code-1.0-MLX-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bsisduck/North-Mini-Code-1.0-MLX-MXFP4 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("bsisduck/North-Mini-Code-1.0-MLX-MXFP4")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use bsisduck/North-Mini-Code-1.0-MLX-MXFP4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bsisduck/North-Mini-Code-1.0-MLX-MXFP4"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bsisduck/North-Mini-Code-1.0-MLX-MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bsisduck/North-Mini-Code-1.0-MLX-MXFP4 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bsisduck/North-Mini-Code-1.0-MLX-MXFP4"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bsisduck/North-Mini-Code-1.0-MLX-MXFP4

Run Hermes

hermes

MLX LM

How to use bsisduck/North-Mini-Code-1.0-MLX-MXFP4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "bsisduck/North-Mini-Code-1.0-MLX-MXFP4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "bsisduck/North-Mini-Code-1.0-MLX-MXFP4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "bsisduck/North-Mini-Code-1.0-MLX-MXFP4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

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"

Downloads last month: -

Safetensors

Model size

30B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for bsisduck/North-Mini-Code-1.0-MLX-MXFP4

Base model

CohereLabs/North-Mini-Code-1.0

Quantized

(14)

this model