Instructions to use EigenLabs/Qwen3.5-9B-MLX-4bit-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EigenLabs/Qwen3.5-9B-MLX-4bit-mtp with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("EigenLabs/Qwen3.5-9B-MLX-4bit-mtp")
config = load_config("EigenLabs/Qwen3.5-9B-MLX-4bit-mtp")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use EigenLabs/Qwen3.5-9B-MLX-4bit-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/Qwen3.5-9B-MLX-4bit-mtp"

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": "EigenLabs/Qwen3.5-9B-MLX-4bit-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use EigenLabs/Qwen3.5-9B-MLX-4bit-mtp 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 "EigenLabs/Qwen3.5-9B-MLX-4bit-mtp"

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 EigenLabs/Qwen3.5-9B-MLX-4bit-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use EigenLabs/Qwen3.5-9B-MLX-4bit-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/Qwen3.5-9B-MLX-4bit-mtp"

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 "EigenLabs/Qwen3.5-9B-MLX-4bit-mtp" \
  --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"

Qwen3.5-9B MLX W4/g64 + Embedded W4 MTP

This is a full vision-language MLX conversion of Qwen/Qwen3.5-9B with the model's native one-layer MTP proposal head embedded in the same indexed safetensors weight set under the mtp.* prefix.

Language target and vision tower: byte-identical to mlx-community/Qwen3.5-9B-MLX-4bit (W4/g64 affine, BF16 scales/biases).
MTP head: the 15 native mtp.* tensors from the source checkpoint, RMSNorm weights converted to the MLX x·w convention (+1) and the 8 linear modules quantized to W4/g64 affine with BF16 scales/biases (~137 MB).
Declared via mtplx_mtp / mtplx_mtp_quantization in config.json (prefix: "mtp.", block_size: 3). The head shares the target embedding and LM head, as intended by the source architecture.

There is no separate MTP repository: the proposal head travels inside the checkpoint, so the draft/target pairing cannot drift.

Measured (M4 Max, 546 GB/s, temperature 0)

Configuration	decode tok/s
target only	47.9–48.5
embedded MTP	73–83

Conversion notes

Raw source mtp.* norms are stored in the Qwen3-Next x·(1+w) convention and MUST be shifted by +1 for MLX runtimes; quantization scales/biases MUST be bfloat16. Raw norms produce a head whose drafts are rejected (slower than no MTP at all); float16 scales fail the assistant load, which serving stacks should surface as a logged fallback to target-only decoding.

Downloads last month: 177

Safetensors

Model size

10B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

4-bit

Model tree for EigenLabs/Qwen3.5-9B-MLX-4bit-mtp

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(512)

this model