dicksondickson/Swift-1.5-Qwen3.8-27b-oQ8e-fp16-mtp
This model is a quantization of: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b
This checkpoint was quantized using oMLX 0.7.0rc1 with imatrix enabled.
FP16 is for M1/M2 chips. For M3/M4/M5 use the BF16 variant:
https://huggingface.co/dicksondickson/Swift-1.5-Qwen3.8-27b-oQ8e-bf16-mtp-MLX
Run the model using oMLX: https://github.com/jundot/omlx
- Downloads last month
- 498
Model size
28B params
Tensor type
U32
·
F16 ·
F32 ·
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