[!IMPORTANT] This quantization was uploaded on 2026-06-30 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

LFM2-1.2B-MLX-oQ8

Quantization details

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