Instructions to use FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit 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("FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit") config = load_config("FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit") # 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
- Pi
How to use FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit"
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": "FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit 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 "FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit"
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 FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit"
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 "FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit" \ --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"
Qwen3.5-4B-thinking-mlx-8bit
A version of Qwen/Qwen3.5-4B, tuned by FiditeNemini for
local agent work and quantised to MLX 8-bit (affine, group size 64). It's a thinking model: answers start
with reasoning in <think>โฆ</think>.
It's the default model of MLX-Minions, a native macOS app that runs local agents on an in-process MLX model. MLX-Minions loads the text path only (via mlx-swift-lm), and the vision weights go unused.
Use
With mlx-lm or mlx-vlm on Apple silicon, as with any MLX Qwen3.5 checkpoint. MLX-Minions downloads a pinned revision and checks every file's SHA-256 before loading it.
Licence
Apache 2.0, the base model's licence.
- Downloads last month
- 82
8-bit