API Try Docs Blog

LFM3-1.7B-MLX-8bit

8-bit MLX version of LFM3-1.7B for Apple Silicon. The weights take 1.84 GB.

Weights use 8-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-8bit \
  --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.