Instructions to use Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mer0vin8ian/Qwen3.5-9B-OptiQ-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("Mer0vin8ian/Qwen3.5-9B-OptiQ-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 Mer0vin8ian/Qwen3.5-9B-OptiQ-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 "Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit"

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": "Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Mer0vin8ian/Qwen3.5-9B-OptiQ-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 "Mer0vin8ian/Qwen3.5-9B-OptiQ-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 Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit

Run Hermes

hermes

OpenClaw new

How to use Mer0vin8ian/Qwen3.5-9B-OptiQ-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 "Mer0vin8ian/Qwen3.5-9B-OptiQ-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 "Mer0vin8ian/Qwen3.5-9B-OptiQ-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"

MLX LM

How to use Mer0vin8ian/Qwen3.5-9B-OptiQ-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 "Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Mer0vin8ian/Qwen3.5-9B-OptiQ-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Move OptiQ sidecars under optiq/ so mlx-vlm / LM Studio don't choke on them

by codelion - opened 13 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

codelion

13 days ago

No description provided.

Move OptiQ sidecars under optiq/ so mlx-vlm / LM Studio don't choke on thembeb121ed

codelion

13 days ago

Thanks for publishing an OptiQ quant! Heads up on a loading issue this fixes.

Loading this model in LM Studio (or anything using mlx-vlm) can fail with Received N parameters not in model for mtp.safetensors: mlx-vlm globs every *.safetensors in the folder and strict-loads the OptiQ sidecar, which the base model has no module for.

This PR moves the OptiQ sidecar(s) (mtp.safetensors / optiq_vision.safetensors) into an optiq/ subfolder. A non-recursive *.safetensors glob doesn't descend into it, so mlx-vlm / LM Studio no longer pick them up and the language tower loads cleanly. config.json is updated to point at the new path, so mlx-optiq still finds them; mlx-lm was already unaffected.

The weights are unchanged — the files are copied server-side, not re-quantized. Fixed upstream in mlx-optiq 0.3.1 (https://pypi.org/project/mlx-optiq/0.3.1/), which is how new quants avoid this. Feel free to merge if it looks good.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment