Instructions to use mlx-community/Qwen3.5-4B-MTP-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Qwen3.5-4B-MTP-bf16 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("mlx-community/Qwen3.5-4B-MTP-bf16")

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
LM Studio

How to use mlx-community/Qwen3.5-4B-MTP-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Qwen3.5-4B-MTP-bf16"

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": "mlx-community/Qwen3.5-4B-MTP-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Qwen3.5-4B-MTP-bf16 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 "mlx-community/Qwen3.5-4B-MTP-bf16"

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 mlx-community/Qwen3.5-4B-MTP-bf16

Run Hermes

hermes

MLX LM

How to use mlx-community/Qwen3.5-4B-MTP-bf16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Qwen3.5-4B-MTP-bf16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Qwen3.5-4B-MTP-bf16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Qwen3.5-4B-MTP-bf16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.5-4B-MTP-bf16

This repository contains Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-4B for use with mlx-vlm speculative decoding.

This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Qwen3.5 4B target checkpoint.

Use with mlx-vlm

uv run mlx_vlm.generate \
  --model Qwen/Qwen3.5-4B \
  --draft-model mlx-community/Qwen3.5-4B-MTP-bf16 \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

For local weights:

uv run mlx_vlm.generate \
  --model /path/to/target-model \
  --draft-model /path/to/Qwen3.5-4B-mtp \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

Model Details

Model type: qwen3_5_mtp
MTP block size: 2
Target architecture: Qwen3.5 4B
Precision: bf16
Runtime: MLX / mlx-vlm
Format: Safetensors with MLX-compatible config and tokenizer files

The stored tensors are unquantized MLX-compatible drafter weights.

Intended Use

Use this repo only as a speculative decoding drafter for compatible Qwen3.5 4B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step.

Limitations

This checkpoint requires runtime support for Qwen/DeepSeek MTP draft models in mlx-vlm. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself.

Please refer to the upstream Qwen/Qwen3.5-4B model card and license terms for model usage constraints.