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

Libraries

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

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-Quality 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-Quality"

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-Quality"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

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-Quality

Run Hermes

hermes

OpenClaw new

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

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-Quality" \
  --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-Quality 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-Quality"

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-Quality"
# 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-Quality",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.5-4B MTPLX Optimized Quality

8-bit (group 64) Qwen3.5-4B with a calibrated native-MTP draft head, built for MTPLX on Apple Silicon. 4.58 GB on disk, ~4.8 GiB peak at load. The highest-fidelity 4B MTPLX ships, with the largest MTP multiplier in the fleet.

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

AR baseline: 87.4 tok/s
MTP depth 3: 191.7 tok/s (2.19x), acceptance 0.91 / 0.76 / 0.62
First-position acceptance: 0.95

The 8-bit trunk keeps output quality close to the BF16 reference while the calibrated draft head converts that fidelity into a 2.2x decode multiplier. The engine reads the tuned depth from mtplx_runtime.json. Runs on any Apple Silicon Mac with 8 GB+ of unified memory.

Provenance

New artifact (July 2026), forged with the fixed MTPLX forge after the 4B zero-acceptance defect (#176) was root-caused: draft-head RMSNorms in the original export are stored zero-centered and must be restored at extraction. The draft head is quantized int4 (group 64) with fc and norms kept in BF16, calibrated so acceptance matches the BF16 head.

Usage

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

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

Downloads last month: 116

Safetensors

Model size

1B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

8-bit

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

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(331)

this model