Files
zeekay 89da15d070 refactor: zen-coder branding - rename examples, add LLM.md and training configs
- Rename Qwen2.5-Coder-* examples to zen-coder-* (consistent Zen branding)
- Add LLM.md knowledge base (symlinked as CLAUDE.md/AGENTS.md/etc.)
- Update .gitignore: exclude model weights and AI symlink files
- Add training configs, inference scripts, test suite
- Add MLX README, model card, Makefile for common operations
2026-02-27 19:06:12 -08:00

1.0 KiB

Zen Coder - MLX Format

Available Formats

  • mlx/: Base FP16 model
  • mlx-4bit/: 4-bit quantized model (smallest, fastest)
  • mlx-8bit/: 8-bit quantized model (balanced)

Usage

Using mlx_lm CLI

# Base model
mlx_lm.generate --model zen-coder/mlx --prompt "Your prompt here"

# 4-bit model (fastest)
mlx_lm.generate --model zen-coder/mlx-4bit --prompt "Your prompt here"

# 8-bit model
mlx_lm.generate --model zen-coder/mlx-8bit --prompt "Your prompt here"

Using Python

from mlx_lm import load, generate

# Load 4-bit model (recommended for speed)
model, tokenizer = load("zen-coder/mlx-4bit")

# Generate text
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=256)
print(response)

Performance on Apple Silicon

Format Memory Speed Quality
FP16 High Slow Best
8-bit Medium Medium Good
4-bit Low Fast Good

Model Sizes

  • mlx/: 0.0 GB
  • mlx-4bit/: 0.0 GB
  • mlx-8bit/: 0.0 GB