What are the hardware requirements for Gemma EPFL?

Gemma EPFL requires approximately 10 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma EPFL and how large is it?

Gemma EPFL is developed by ghemdd, a model with 2.5b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Gemma EPFL?

Gemma EPFL is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma EPFL by ghemdd — VRAM 10GB, 8K context

Name: Gemma EPFL
Author: ghemdd

Gemma EPFL is an open-source language model by ghemdd. Features: 2.5b LLM, VRAM: 10GB, Context: 8K, License: mit, LLM Explorer Score: 0.13.

Arxiv:1910.09700 Conversational Endpoints compatible Gemma Llama-factory Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ghemdd/gemma-EPFL

Gemma EPFL Parameters and Internals

LLM Name	Gemma EPFL
Repository 🤗	https://huggingface.co/ghemdd/gemma-EPFL
Model Size	2.5b
Required VRAM	10 GB
Updated	2026-07-18
Maintainer	ghemdd
Model Type	gemma
Model Files	2.1 GB: 1-of-6 1.9 GB: 2-of-6 1.9 GB: 3-of-6 1.9 GB: 4-of-6 1.9 GB: 5-of-6 0.3 GB: 6-of-6
Model Architecture	GemmaForCausalLM
License	mit
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	float32

Rank the Gemma EPFL capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Gemma EPFL

Best Alternatives	Context / RAM	Downloads
Sherlock Gemma Finetuned	8K / 2.2 GB	6
Geko3	8K / 5.1 GB	7
Gemma Ko V01	8K / 5.1 GB	11
M3 Sft Orca It Base	8K / 10 GB	11
M3 Sft Orca It Base	8K / 10 GB	5
Orca Gemma It DPO	8K / 10 GB	5
M3 Sft It DPO	8K / 10 GB	10
M3 Sft Gemma It	8K / 10 GB	9
M3 Sft Gemma	8K / 10 GB	7
Orca Gemma It DPO	8K / 10 GB	7

Note: green Score (e.g. "73.2") means that the model is better than ghemdd/gemma-EPFL.