Has been quantized using OMLX 0.4.2.dev2 (1444)
This is the FP16 version which is optimal for Apple Silicon M1 and M2 Mac devices. This is the version that was released approx 4th June 2026 at 13:00 GMT
All thanks goes to the creators of all of the above, I merely just converted the model for those that cannot
- Downloads last month
- 9
Model size
3B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for wezzel98765/gemma-4-12B-oQ6-fp16
Base model
google/gemma-4-12B