How to use from
Pi
Start the MLX server
# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LiquidAI/LFM3-1.7B-MLX-4bit"
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": "LiquidAI/LFM3-1.7B-MLX-4bit"
        }
      ]
    }
  }
}
Run Pi
# Start Pi in your project directory:
pi
Quick Links

LFM3-1.7B-MLX-4bit

4-bit MLX version of LFM3-1.7B for Apple Silicon. The weights take 0.97 GB.

Weights use 4-bit affine quantization with groups of 64.

Find architecture and usage details in the original model card.

Use with MLX-VLM


Requires MLX-VLM 0.7.11 or later:

pip install -U "mlx-vlm>=0.7.11"
python -m mlx_vlm.generate --model LiquidAI/LFM3-1.7B-MLX-4bit \
  --prompt "What is the capital of Australia?" --enable-thinking \
  --temperature 0.1 --top-k 50 --repetition-penalty 1.1 --max-tokens 16384

Reasoning stays off unless you pass --enable-thinking. For math and science, use --temperature 1.0 --top-p 0.95 --top-k 20 --repetition-penalty 1.0 instead. No mlx-lm release loads LFM3 yet; support is in review in ml-explore/mlx-lm#2016. More options in the MLX guide.

Downloads last month
18,263
Safetensors
Model size
2B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for LiquidAI/LFM3-1.7B-MLX-4bit

Quantized
(166)
this model