LFM2.5-8B-A1B

4-bit affine quantization of LiquidAI/LFM2.5-8B-A1B, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).

Conversion

ffai convert LiquidAI/LFM2.5-8B-A1B --bits 4

See also

• FFAI — fast Apple Silicon LLM inference. Model.load("LiquidAI/LFM2.5-8B-A1B") runs this checkpoint end-to-end.
• FFAI quickstart
• FFAI quantization docs