qwen3.5-9b-spotlight-r3-optiq-mlx

Qwen/Qwen3.5-9B, quantized with OptiQ by tomvaillant for Apple Silicon.

community

On disk8.0 GB

Memoryabout 11 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 tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

OptiQ Code

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

optiq serve --model tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx
optiq code

OptiQ Lab

optiq lab --model tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

Claude Code

optiq run claude -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

Codex

optiq run codex -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

OpenCode

optiq run opencode -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

Mistral Vibe

optiq run vibe -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

Hermes Agent

optiq run hermes -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

OpenClaw

optiq run openclaw -m tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx

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("tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen3.5
Base model	Qwen/Qwen3.5-9B
Size on disk	8.0 GB
Memory needed	about 11 GB
Images	no, text only
Downloads	69 in the last month
Updated	2026-11-06
Hugging Face	tomvaillant/qwen3.5-9b-spotlight-r3-optiq-mlx