license: apache-2.0 base_model: orcarouter/Qwen3.8-27B-Uncensored base_model_relation: quantized library_name: mlx pipeline_tag: text-generation language:

en tags:
mlx
optiq
quantized
4bit
mixed-precision
qwen3.8
reasoning
long-context
mtp
multi-token-prediction
function-calling
tool-use
agentic
uncensored
apple-silicon

mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. All OptiQ quants · Docs

OptiQ mixed-precision quant of orcarouter/Qwen3.8-27B-Uncensored, a Qwen3.8-family reasoning model with a bundled MTP speculation head. 19 GB on disk.

What it is

Property	Value
Base	orcarouter/Qwen3.8-27B-Uncensored (Qwen3.8, 27B)
Method	OptiQ mixed-precision, per-layer 4/8-bit
Bit allocation	Reused from the Qwen3.8-27B OptiQ recipe: the architecture is identical, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed
Layer split	237 components at 4-bit, 261 at 8-bit
Group size	64
On disk	19 GB
MTP	Speculation head preserved in `optiq/mtp.safetensors` for faster decode via `optiq serve --draft-model`

Following the naming llama.cpp uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.

Run it

Qwen3.8 and the MTP sidecar register through OptiQ, so import optiq once before loading:

pip install "mlx-optiq>=0.4.27"

import optiq  # registers the arch + MTP sidecar
from mlx_lm import load, generate

model, tok = load("mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit")
prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Explain mixed-precision quantization in two sentences."}],
    tokenize=False, add_generation_prompt=True,
)
print(generate(model, tok, prompt=prompt, max_tokens=400))

For an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:

optiq serve --model mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit

This is a reasoning model, so give it a generous token budget.

Links

Project website: mlx-optiq.com
All OptiQ quants: mlx-optiq.com/models
Base model: orcarouter/Qwen3.8-27B-Uncensored

mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. All OptiQ quants · Docs

OptiQ mixed-precision quant of orcarouter/Qwen3.8-27B-Uncensored, a Qwen3.8-family reasoning model with a bundled MTP speculation head. 19 GB on disk.

What it is

Property

Value

Base

orcarouter/Qwen3.8-27B-Uncensored (Qwen3.8, 27B)

Method

OptiQ mixed-precision, per-layer 4/8-bit

Bit allocation

Reused from the Qwen3.8-27B OptiQ recipe: the architecture is identical, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed

Layer split

237 components at 4-bit, 261 at 8-bit

Group size

On disk

19 GB

MTP

Speculation head preserved in optiq/mtp.safetensors for faster decode via optiq serve --draft-model

Following the naming llama.cpp uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.

Run it

Qwen3.8 and the MTP sidecar register through OptiQ, so import optiq once before loading:

pip install "mlx-optiq>=0.4.27"

import optiq # registers the arch + MTP sidecar from mlx_lm import load, generate model, tok = load("mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit") prompt = tok.apply_chat_template( [{"role": "user", "content": "Explain mixed-precision quantization in two sentences."}], tokenize=False, add_generation_prompt=True, ) print(generate(model, tok, prompt=prompt, max_tokens=400))

For an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:

optiq serve --model mlx-community/Qwen3.8-27B-Uncensored-OptiQ-4bit

This is a reasoning model, so give it a generous token budget.