What are the hardware requirements for Jev Gemma4?

Jev Gemma4 requires approximately 10.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Jev Gemma4 and how large is it?

Jev Gemma4 is developed by Mahi2305, a model with 5.1b 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 Jev Gemma4?

Jev Gemma4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Jev Gemma4 by Mahi2305 — VRAM 10.3GB

Name: Jev Gemma4
Author: Mahi2305

Jev Gemma4 is an open-source language model by Mahi2305. Features: 5.1b LLM, VRAM: 10.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-4-e2b... Conversational En Endpoints compatible Gemma4 Image-text-to-text Quantized Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/Mahi2305/jev-gemma4

Jev Gemma4 Parameters and Internals

LLM Name	Jev Gemma4
Repository 🤗	https://huggingface.co/Mahi2305/jev-gemma4
Base Model(s)	...emma 4 E2B It Unsloth Bnb 4bit unsloth/gemma-4-E2B-it-unsloth-bnb-4bit
Model Size	5.1b
Required VRAM	10.3 GB
Updated	2026-10-13
Maintainer	Mahi2305
Model Type	gemma4
Model Files	1.4 GB: 1-of-5 4.7 GB: 2-of-5 1.6 GB: 3-of-5 1.6 GB: 4-of-5 1.0 GB: 5-of-5
Supported Languages	en
Quantization Type	4bit
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Jev Gemma4 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 Jev Gemma4

Best Alternatives	Context / RAM	Downloads	Likes
...emma 4 E2B It Unsloth Bnb 4bit	0K / 8.1 GB	78251	11
... 4 E2B It Qat Q4 0 Unquantized	0K / 10.2 GB	13412	32
Sdam Gemma4 E2B Merged Bf16	0K / 10.2 GB	424	1
... 4 E2B It Qat Q4 0 Unquantized	0K / 10.2 GB	3007	4
Dama Aibrain	0K / 10.3 GB	38	1
Dama Aibrain	0K / 10.3 GB	323	0
My Brain V1	0K / 10.3 GB	35	0
...mma 4 E2B It Qat Q4 0 W4a16 Ct	0K / 0 GB	30	0
Gemma 4 E2B Unsloth Bnb 4bit	0K / 9 GB	2032	5
...emma4 E2B MIXED NO TAG E3 BF16	0K / 10.2 GB	27	1

Note: green Score (e.g. "73.2") means that the model is better than Mahi2305/jev-gemma4.