lemmy-mlx-8bit / README.md
Snider
feat: initial mlx 8bit quant, converted from LetheanNetwork/lemmy bf16
eb7291e
---
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](https://huggingface.co/LetheanNetwork/lemmy)'s bf16
safetensors via `mlx_lm.convert`. Higher-precision sibling of
[`LetheanNetwork/lemmy-mlx`](https://huggingface.co/LetheanNetwork/lemmy-mlx)
(4-bit). For the LEK-merged variant see
[`lthn/lemmy`](https://huggingface.co/lthn/lemmy).
## License
Apache 2.0, subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/docs/gemma_4_license).