README.md

metadata

language:
  - en
license: eupl-1.2
library_name: mlx
tags:
  - mlx
  - safetensors
  - 4-bit
  - transformers
  - 8-bit
  - gguf
  - gemma4
base_model:
  - google/gemma-4-e4b-it
base_model_relation: quantized
pipeline_tag: any-to-any
datasets:
  - lthn/LEM-research

Lemma

A Gemma 4 E4B finetune by lthn.ai — EUPL-1.2

Use

MLX: 4bit, 5bit, 6bit, 8bit, bf16, mxfp4, mxfp8, nvfp4

Lemer (E2B) · Lemma (E4B) · Lemmy (26B) · Lemrd (31B)

Base

google/gemma-4-e4b-it

More

• lthn.ai
• Lethean Network

Licence

Training data and adapter: EUPL-1.2 Base model: Apache 2.0