LFM2.5-8B-A1B-oQ8e
This model was quantized using oQ (oMLX v0.5.4rc1) mixed-precision quantization.
Quantization details
- Model type: lfm2_moe
- Bits: 8
- Group size: 64
- Format: MLX safetensors
Notes
very fast on M3 Max 48 GB
- Downloads last month
- 78
Model size
2B params
Tensor type
BF16
路
U32 路
F32 路
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support