Hugging Face's logo

LetheanNetwork
/
lemma-mlx-bf16

Image-Text-to-Text
MLX
Safetensors
gemma4
apple-silicon
bf16
on-device
conversational
Model card Files
xet
 Community

LetheanNetwork/lemma-mlx-bf16

Gemma 4 in MLX format, full bf16 precision, converted from LetheanNetwork/lemma's bf16 safetensors via mlx_lm.convert --dtype bfloat16 (no quantization). The full-precision reference for the MLX family. For the LEK-merged variant see lthn/lemma.

License

Apache 2.0, subject to the Gemma Terms of Use.

Downloads last month
6
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LetheanNetwork/lemma-mlx-bf16

Base model

google/gemma-4-E4B
Finetuned
google/gemma-4-E4B-it
Quantized
LetheanNetwork/lemma
Finetuned
(2)
this model