Downloads · 30 days
13
13% of all-time downloads
dwyschka/gemma-4-12B-it-oQ4-fp16
gemma-4-12B-it-oQ4-fp16 is a machine learning model from dwyschka. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Update 9:30pm GMT - re quantized using OMLX 0.4.2.dev2 (1444)
Downloads · 30 days
13
13% of all-time downloads
All-time downloads
98
Public
Parameters
12B
7.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.1 GB · 100%
How the weights are stored.
U3211.9B · 100%
From the Hugging Face model README
Update 9:30pm GMT - re 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