Qwen3.5-122B-A10B-OptiQ-2bit

Qwen/Qwen3.5-122B-A10B, quantized by OptiQ for Apple Silicon; mixture-of-experts, takes images.

visionMoE

On disk46.8 GB

Memoryabout 55 GB

Imagesyes

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/Qwen3.5-122B-A10B-OptiQ-2bit

OptiQ Code

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

optiq serve --model mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit
optiq code

OptiQ Lab

optiq lab --model mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

Claude Code

optiq run claude -m mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

Codex

optiq run codex -m mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

OpenCode

optiq run opencode -m mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

Mistral Vibe

optiq run vibe -m mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

Hermes Agent

optiq run hermes -m mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit

OpenClaw

optiq run openclaw -m mlx-community/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-OptiQ-2bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen3.5 MoE
Base model	Qwen/Qwen3.5-122B-A10B
Size on disk	46.8 GB
Memory needed	about 55 GB
Images	yes, through optiq serve and the Lab
Downloads	543 in the last month
Updated	2026-09-15
Hugging Face	mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit