Instructions to use kqw8/Qwen3.5-27B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kqw8/Qwen3.5-27B-MLX-4bit 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("kqw8/Qwen3.5-27B-MLX-4bit")

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 kqw8/Qwen3.5-27B-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "kqw8/Qwen3.5-27B-MLX-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kqw8/Qwen3.5-27B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use kqw8/Qwen3.5-27B-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "kqw8/Qwen3.5-27B-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "kqw8/Qwen3.5-27B-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "kqw8/Qwen3.5-27B-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use kqw8/Qwen3.5-27B-MLX-4bit 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 "kqw8/Qwen3.5-27B-MLX-4bit"

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 kqw8/Qwen3.5-27B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kqw8/Qwen3.5-27B-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "kqw8/Qwen3.5-27B-MLX-4bit"

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 "kqw8/Qwen3.5-27B-MLX-4bit" \
  --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"

Qwen3.5-27B MLX 4-bit

This is an unofficial MLX 4-bit quantization of Qwen/Qwen3.5-27B.

It was converted from the official Hugging Face weights with mlx-lm. This repository is not affiliated with or endorsed by Qwen or Alibaba.

Conversion

mlx_lm.convert \
  --hf-path Qwen/Qwen3.5-27B \
  --mlx-path Qwen3.5-27B-MLX-4bit \
  --quantize \
  --q-bits 4 \
  --q-group-size 64

Quantization reported by mlx_lm.convert:

Quantized model with 4.501 bits per weight.

Local Usage

mlx_lm.generate \
  --model Qwen3.5-27B-MLX-4bit \
  --prompt "用一句话说明你是什么模型。" \
  --max-tokens 80 \
  --chat-template-config '{"enable_thinking": false}'

OpenAI-compatible local server:

mlx_lm.server \
  --model Qwen3.5-27B-MLX-4bit \
  --host 127.0.0.1 \
  --port 8080 \
  --chat-template-args '{"enable_thinking": false}'

Smoke Test

Tested on Apple Silicon with mlx-lm 0.31.3:

Prompt: 19 tokens, 41.697 tokens-per-sec
Generation: 21 tokens, 15.582 tokens-per-sec
Peak memory: 15.411 GB

Only text generation has been smoke-tested. The base model is multimodal, but this MLX conversion has not yet been validated for image input.

License

The original model is released under Apache-2.0. See the upstream model page and license:

Downloads last month: 24

Safetensors

Model size

27B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for kqw8/Qwen3.5-27B-MLX-4bit

Base model

Qwen/Qwen3.5-27B

Quantized

(221)

this model