Qwen3.6-27B-Opus-Distill-OptiQ-4bit

TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2, quantized with OptiQ by caslca for Apple Silicon.

communityMTP head

On disk19.5 GB

Memoryabout 24 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 caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

OptiQ Code

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

optiq serve --model caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

Claude Code

optiq run claude -m caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

Codex

optiq run codex -m caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

OpenCode

optiq run opencode -m caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

Mistral Vibe

optiq run vibe -m caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

Hermes Agent

optiq run hermes -m caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit

OpenClaw

optiq run openclaw -m caslca/Qwen3.6-27B-Opus-Distill-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("caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen3.5
Base model	TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
Size on disk	19.5 GB
Memory needed	about 24 GB
Images	no, text only
MTP head	included
Downloads	158 in the last month
Updated	2026-09-14
Hugging Face	caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit