Gemma 4 26B A4B MoE in MLX format, full bf16 precision, converted from LetheanNetwork/lemmy'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/lemmy.

Apache 2.0, subject to the Gemma Terms of Use.