gemma-4-12B-it-4bit-MLX-mirror
Mirror. Unmodified copy of files from mlx-community/gemma-4-12B-it-4bit at revision 73bcf09092aa277861d5a191b989b666f7f32e8f; every file's sha256 equals the upstream LFS hash. Kept by Think Spread so its tests and tools can fetch a fixed copy (tempo9 --hf thinkspread/gemma-4-12B-it-4bit-MLX-mirror). For other quantizations, documentation and updates use the upstream repository.
| file | size | sha256 |
|---|---|---|
model-00001-of-00002.safetensors |
5.35 GB | 0d58feed0c98a69c07317b4481aeae5ab2785f12a496ea96ab24c4842808de78 |
model-00002-of-00002.safetensors |
1.39 GB | 5b00a1bcb596ce6e827b4cdea6ecf2a0f35bb01306eb87c1ea4b3bcde36c7755 |
Base model: google/gemma-4-12b-it. License: Apache 2.0, as published by Google for Gemma 4 and by the upstream repository.
- Downloads last month
- 70
Model size
12B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support