[!IMPORTANT] This quantization was uploaded on 2026-08-18 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

LFM2.5-1.2B-Thinking-MLX-oQ8e

Quantization details

• Model type: lfm2
• Bits: 8
• Group size: 64
• Format: MLX safetensors