Qwen3.8-27B-Uncensored-OptiQ-4bit
orcarouter/Qwen3.8-27B-Uncensored, quantized with OptiQ by j-llm for Apple Silicon; takes images.
communityvisionMTP headOn disk21.5 GB
Memoryabout 26 GB
Capability Score91.69
Imagesyes
Use it
Install
pip install mlx-optiqServe it
An OpenAI- and Anthropic-compatible server on this Mac. Every app below can use it.
optiq serve --model j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitOptiQ Code
The terminal coding agent uses whatever model optiq serve is running.
optiq serve --model j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bit
optiq codeOptiQ Lab
optiq lab --model j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitClaude Code
optiq run claude -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitCodex
optiq run codex -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitOpenCode
optiq run opencode -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitMistral Vibe
optiq run vibe -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitHermes Agent
optiq run hermes -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitOpenClaw
optiq run openclaw -m j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bitoptiq 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("j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))Details
| Family | Qwen · Qwen docs |
|---|---|
| Architecture | Qwen3.5 |
| Base model | orcarouter/Qwen3.8-27B-Uncensored |
| Size on disk | 21.5 GB |
| Memory needed | about 26 GB |
| Images | yes, through optiq serve and the Lab |
| MTP head | included |
| Capability Score | 91.69 (from the model card) |
| Downloads | 885 in the last month |
| Updated | 2026-10-11 |
| Hugging Face | j-llm/Qwen3.8-27B-Uncensored-OptiQ-4bit |