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
This model was quantized using oQ (oMLX v0.6.2) mixed-precision quantization.
Quantization details
- Model type: lfm2
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 24
Model size
0.3B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support