MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

dalatexcoder/MiniCPM5-2B-heretic-ara, quantized with OptiQ by dalatexcoder for Apple Silicon.

community

On disk1.6 GB

Memoryabout 3 GB

Use it

Install

pip install mlx-optiq

Serve it

An OpenAI- and Anthropic-compatible server on this Mac. Every app below can use it.

optiq serve --model dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

OptiQ Code

The terminal coding agent uses whatever model optiq serve is running.

optiq serve --model dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed
optiq code

OptiQ Lab

optiq lab --model dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

Claude Code

optiq run claude -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

Codex

optiq run codex -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

OpenCode

optiq run opencode -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

Mistral Vibe

optiq run vibe -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

Hermes Agent

optiq run hermes -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

OpenClaw

optiq run openclaw -m dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed

optiq run starts optiq serve if it is not running, sets the agent up for this session only, and stops the server when the agent exits.

mlx-lm, text only

from mlx_lm import load, generate

model, tokenizer = load("dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	MiniCPM · MiniCPM docs
Architecture	Llama
Base model	dalatexcoder/MiniCPM5-2B-heretic-ara
Size on disk	1.6 GB
Memory needed	about 3 GB
Images	no, text only
Downloads	91 in the last month
Updated	2026-10-13
Hugging Face	dalatexcoder/MiniCPM5-2B-ARA-MLX-4Bit-optiq-mixed