Instructions to use adrianmurray/Qwen3.8-27B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adrianmurray/Qwen3.8-27B-MLX-6bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("adrianmurray/Qwen3.8-27B-MLX-6bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use adrianmurray/Qwen3.8-27B-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adrianmurray/Qwen3.8-27B-MLX-6bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "adrianmurray/Qwen3.8-27B-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use adrianmurray/Qwen3.8-27B-MLX-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "adrianmurray/Qwen3.8-27B-MLX-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "adrianmurray/Qwen3.8-27B-MLX-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "adrianmurray/Qwen3.8-27B-MLX-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use adrianmurray/Qwen3.8-27B-MLX-6bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adrianmurray/Qwen3.8-27B-MLX-6bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default adrianmurray/Qwen3.8-27B-MLX-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use adrianmurray/Qwen3.8-27B-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adrianmurray/Qwen3.8-27B-MLX-6bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "adrianmurray/Qwen3.8-27B-MLX-6bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-27B MLX 6-bit

This is a modified, 6-bit MLX quantization of Alibaba Cloud's official Qwen/Qwen3.8-27B checkpoint. It is intended for local inference on Apple Silicon and can be paired with the separately distributed native-MTP artifact from the same source revision.

Artifact identity

Base model: Qwen/Qwen3.8-27B
Base revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
Quantization: affine 6-bit, group size 64
Native context length: 262,144 tokens
Weight shards: five MLX SafeTensors files
Approximate on-disk size: 20 GB

The internal Transformers/MLX architecture identifiers retain the qwen3_5 name because Qwen3.8 uses the compatible architectural foundation. Those implementation identifiers do not change the checkpoint identity.

Reproduction

Using MLX LM 0.31.3 and MLX 0.32.0:

mlx_lm.convert \
  --hf-path /path/to/Qwen3.8-27B \
  --mlx-path /path/to/Qwen3.8-27B-MLX-6bit \
  --quantize --q-bits 6 --q-group-size 64 --q-mode affine

The source directory must correspond to the exact base revision above. Verify the converted files against SHA256SUMS before publishing or loading them.

Use with Qwen Prime Runtime

qwen-prime-runtime configure \
  --target /path/to/Qwen3.8-27B-MLX-6bit \
  --draft /path/to/Qwen3.8-27B-MTP-MLX-6bit
qwen-prime-runtime doctor
qwen-prime-runtime serve

Performance

No throughput is guaranteed. On the development M4 Max, a warm 256-token coding request measured approximately 26 server tokens/second with 53.9% draft acceptance. A direct block-size sweep measured approximately 28 tokens/second at block size four. Results vary with hardware, prompt length, cache state, generation length, and acceptance ratio.

License and attribution

The original Qwen3.8-27B model is Copyright 2026 Alibaba Cloud and is licensed under Apache License 2.0. This directory includes the original license. The weights and metadata in this repository were modified by conversion and quantization for MLX; see NOTICE and quantization_provenance.json.

The Apache license does not grant trademark rights. This is an independent derivative and is not endorsed by Alibaba Cloud or the Qwen team.

Downloads last month: 446

Safetensors

Model size

6B params

Tensor type

BF16

U32

MLX

Hardware compatibility

6-bit

Model tree for adrianmurray/Qwen3.8-27B-MLX-6bit

Base model

Qwen/Qwen3.8-27B

Quantized

(542)

this model