LetheanNetwork/lemma-mlx-8bit

Gemma 4 in MLX format, 8-bit quantized, converted from LetheanNetwork/lemma's bf16 safetensors via mlx_lm.convert. Higher-precision sibling of LetheanNetwork/lemma-mlx (4-bit). For the LEK-merged variant see lthn/lemma.

License

Apache 2.0, subject to the Gemma Terms of Use.

Downloads last month
16
MLX
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

Model tree for LetheanNetwork/lemma-mlx-8bit

Quantized
(2)
this model