What are the hardware requirements for Gemma 4 E4B It?

Gemma 4 E4B It requires approximately 16 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 E4B It and how large is it?

Gemma 4 E4B It is developed by unsloth, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Gemma 4 E4B It perform on standard benchmarks?

Gemma 4 E4B It has the following published scores: LMSYS ELO 1318. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 4 E4B It by unsloth — VRAM 16GB

Name: Gemma 4 E4B It
Author: unsloth

Gemma 4 E4B It is an open-source language model by unsloth. Features: 8b LLM, VRAM: 16GB, License: apache-2.0, LLM Explorer Score: 0.46, ELO: 1318.

Base model:finetune:google/gem... Base model:google/gemma-4-e4b-... Conversational Gemma Gemma4 Google Image-text-to-text Region:us Safetensors Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/gemma-4-E4B-it

Gemma 4 E4B It Benchmarks

LMSys ELO 1318 vs 1272 (so35) 3.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Gemma 4 E4B It Parameters and Internals

LLM Name	Gemma 4 E4B It
Repository 🤗	https://huggingface.co/unsloth/gemma-4-E4B-it
Base Model(s)	Gemma 4 E4B It google/gemma-4-E4B-it
Model Size	8b
Required VRAM	16 GB
Updated	2026-07-07
Maintainer	unsloth
Model Type	gemma4
Model Files	16.0 GB
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Transformers Version	5.5.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Gemma 4 E4B It 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

Quantized Models of the Gemma 4 E4B It

Model	Likes	Downloads	VRAM
Gemma4 1 0 8 Sft 16bit Vllm	0	29	16 GB

Best Alternatives to Gemma 4 E4B It

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E4B It	0K / 16 GB	4027807	1785
...DIA Nemotron 3.5 Bolt E4B BF16	0K / 15.9 GB	3418	56
Gemma 4 E4B	0K / 16 GB	268109	386
...Nemotron 3.5 Bolt E4B MLX OQ8e	0K / 8.9 GB	150	1
Lite OmniJev	0K / 32.1 GB	184	1
Vishwamai Stage1	0K / 16 GB	472	0
Linne Sprout 1 0	0K / 16 GB	35	1
Gemma4 E4B 8B Heretic Ultra	0K / 16 GB	98	0
Gemma 4 E4B It FP8 Dynamic	0K / 12 GB	31	1
Gemma E4B Mt B Split3	0K / 16 GB	98	0

Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-4-E4B-it.