Lemer

A Gemma 4 E2B finetune by lthn.ai — EUPL-1.2

Ollama: ollama run hf.co/lthn/lemer:Q4_K_M

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

GGUF: BF16, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q3_K_M

HF Transformers: on main (4-bit NF4 + bf16 in hf-bf16/)

Base

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

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Quantized

(45)

this model