lemmy-mlx-8bit / README.md
Snider
feat: initial mlx 8bit quant, converted from LetheanNetwork/lemmy bf16
eb7291e
metadata
library_name: mlx
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: image-text-to-text
base_model:
  - LetheanNetwork/lemmy
base_model_relation: quantized
tags:
  - gemma4
  - mlx
  - apple-silicon
  - 8bit
  - moe
  - mixture-of-experts
  - on-device
  - conversational

LetheanNetwork/lemmy-mlx-8bit

Gemma 4 26B A4B MoE in MLX format, 8-bit quantized, converted from LetheanNetwork/lemmy's bf16 safetensors via mlx_lm.convert. Higher-precision sibling of LetheanNetwork/lemmy-mlx (4-bit). For the LEK-merged variant see lthn/lemmy.

License

Apache 2.0, subject to the Gemma Terms of Use.