zenlm/zen-coder-24b-mlx

Zen Coder 24B (MLX)

Optimized MLX quantization of Zen Coder 24B for Apple Silicon.

Specs

Property	Value
Parameters	24B
Format	MLX 4-bit quantized
License	Apache 2.0
Developer	Hanzo AI

Usage

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("zenlm/zen-coder-24b-mlx")

prompt = "Write a Python function to sort a list"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

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

Links

• Zen LM | Hanzo AI
• GGUF Format
• All Zen Models