minicpm5-deploy-mlx

Installation
SKILL.md

Deploy MiniCPM5-1B with MLX (Apple Silicon)

Apple's on-device tensor framework. Highest throughput on M-series. Stays inside one Python process — no separate server, no llama.cpp build chain.

Required input

Var Example Default
MLX_REPO openbmb/MiniCPM5-1B-MLX (pre-converted 4-bit affine) required
OR HF_REPO + QUANT openbmb/MiniCPM5-1B, 4bit or bf16 for local conversion
MAX_TOKENS 200 200

Steps

1. Install (once)

pip install "mlx-lm>=0.31" "gguf"
Installs
3
Repository
openbmb/minicpm
GitHub Stars
10.5K
First Seen
Jun 1, 2026
minicpm5-deploy-mlx — openbmb/minicpm