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

OpenClaw new

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"

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

Qwen3.8-27B-MLX-6bit

This repository contains the 6-bit MLX quantization of Qwen3.8-27B, optimized for ultra-fast local inference on Apple Silicon (M1/M2/M3/M4 Max/Ultra/Pro).

🚀 Key Specifications

Target Architecture: Qwen 3.8 (27B Parameters)
Quantization: 6-bit group-size 64 MLX weights
Context Length: 32k tokens (scalable up to 128k+)
Memory Footprint: ~21.8 GB Unified Memory
Recommended Hardware: Apple Silicon Mac with 32GB+ Unified Memory (runs comfortably on M-series Pro/Max/Ultra).

💻 Quickstart with MLX-LM

1. Install MLX LM

pip install -U mlx-lm

2. Run Single-Shot Generation

python -m mlx_lm.generate \
  --model username/Qwen3.8-27B-MLX-6bit \
  --prompt "Write a Swift 6 actor for caching network responses." \
  --max-tokens 1024 \
  --temp 0.2

3. Launch Local OpenAI-Compatible Server

python -m mlx_lm.server \
  --model username/Qwen3.8-27B-MLX-6bit \
  --port 8000

⚡ Speculative Decoding (DFlash)

When paired with the companion Qwen3.8-27B-DFlash speculative draft model, this 6-bit model achieves up to 2.5x–3.2x throughput speedups (45–60+ tokens/sec) on Apple Silicon M-series chips while maintaining 100% exact mathematical output fidelity.

📄 License

Apache 2.0 License. Based on the Qwen 3 model series.

Downloads last month: -

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

(404)

this model