Instructions to use Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed 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("Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed")

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 Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed"

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": "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed 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 "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed"

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 Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed

Run Hermes

hermes

OpenClaw new

How to use Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed"

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 "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed" \
  --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 Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed"

Run an OpenAI-compatible server

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

Qwen3.5-4B MTPLX Optimized Speed

4-bit (group 64) Qwen3.5-4B with a calibrated native-MTP draft head, built for MTPLX on Apple Silicon. 2.47 GB on disk, ~2.9 GiB peak at load. The fastest model MTPLX ships.

Measured on an M5 Max (max fans, MTPLX 2.2.0, deterministic suite):

AR baseline: 133.6 tok/s
MTP depth 3: 227.8 tok/s (1.71x), first-position acceptance 0.95

The engine reads the tuned depth from mtplx_runtime.json; no manual configuration needed. Runs on any Apple Silicon Mac with 8 GB+ of unified memory.

July 2026 rebuild (important)

Earlier revisions of this repo shipped a defective MTP sidecar: the RMSNorm weights were stored in the raw zero-centered convention and never restored, so the draft head proposed garbage and MTP made the model slower than plain decoding (reported as #176, thanks lBroth). This revision is rebuilt from source with the fixed forge. MTPLX 2.2.0+ also detects and heals the old sidecar at load, so existing downloads recover without re-downloading.

Usage

Pick "Qwen 3.5 4B Optimized Speed" in the MTPLX app, or:

mtplx serve --model Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed

Downloads last month: 862

Safetensors

Model size

0.7B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for Youssofal/Qwen3.5-4B-MTPLX-Optimized-Speed

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(318)

this model