dicksondickson/VeriLoop-E2-oQ5e-mtp-bf16-MLX
This model is a quantization of: https://huggingface.co/tsinghua-sigs-robot-lab/VeriLoop-E2
This checkpoint was quantized using oMLX 0.7.0 with imatrix enabled.
Important tensors are left at bf16 which is for Apple M3 chips and later.
Run the model using oMLX: https://github.com/jundot/omlx
- Downloads last month
- 32
Model size
28B params
Tensor type
U32
·
BF16 ·
U8 ·
I8 ·
I16 ·
I64 ·
I32 ·
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support