LLaDA2.2-flash-OptiQ-2bit

inclusionAI/LLaDA2.2-flash, quantized by OptiQ for Apple Silicon; mixture-of-experts.

MoE

On disk38.9 GB

Memoryabout 46 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 mlx-community/LLaDA2.2-flash-OptiQ-2bit

OptiQ Code

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

optiq serve --model mlx-community/LLaDA2.2-flash-OptiQ-2bit
optiq code

OptiQ Lab

optiq lab --model mlx-community/LLaDA2.2-flash-OptiQ-2bit

Claude Code

optiq run claude -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

Codex

optiq run codex -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

OpenCode

optiq run opencode -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

Mistral Vibe

optiq run vibe -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

Hermes Agent

optiq run hermes -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

OpenClaw

optiq run openclaw -m mlx-community/LLaDA2.2-flash-OptiQ-2bit

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/LLaDA2.2-flash-OptiQ-2bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	LLaDA2
Architecture	LLaDA2
Base model	inclusionAI/LLaDA2.2-flash
Size on disk	38.9 GB
Memory needed	about 46 GB
Images	no, text only
Downloads	94 in the last month
Updated	2026-07-24
Hugging Face	mlx-community/LLaDA2.2-flash-OptiQ-2bit