← Models

Xing4.0-29B-A4B-OptiQ-4bit

XingChen-AGI/Xing4.0-29B-A4B, quantized by OptiQ for Apple Silicon; mixture-of-experts.

MoE

On disk20.6 GB

Memoryabout 25 GB

Capability Score66.71

Capability Score breakdown

The six metrics behind this model's Capability Score of 66.71, as reported in the model card.

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 mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

OptiQ Code

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

optiq serve --model mlx-community/Xing4.0-29B-A4B-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

Claude Code

optiq run claude -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

Codex

optiq run codex -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

OpenCode

optiq run opencode -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

Mistral Vibe

optiq run vibe -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

Hermes Agent

optiq run hermes -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

OpenClaw

optiq run openclaw -m mlx-community/Xing4.0-29B-A4B-OptiQ-4bit

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("mlx-community/Xing4.0-29B-A4B-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Xing4.0 · Xing4.0 docs
Architecture	Xing4.0
Base model	XingChen-AGI/Xing4.0-29B-A4B
Size on disk	20.6 GB
Memory needed	about 25 GB
Images	no, text only
Capability Score	66.71 (from the model card)
Downloads	917 in the last month
Updated	2026-09-23
Hugging Face	mlx-community/Xing4.0-29B-A4B-OptiQ-4bit