What are the hardware requirements for Gemma 3 4B Est V1?

Gemma 3 4B Est V1 requires approximately 8.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 3 4B Est V1 and how large is it?

Gemma 3 4B Est V1 is developed by Abdusin, a model with 4b 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 3 4B Est V1?

Gemma 3 4B Est V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 3 4B Est V1 by Abdusin — VRAM 8.6GB

Name: Gemma 3 4B Est V1
Author: Abdusin

Gemma 3 4B Est V1 is an open-source language model by Abdusin. Features: 4b LLM, VRAM: 8.6GB, License: gemma, LLM Explorer Score: 0.33.

Arxiv:2310.03389 Arxiv:2510.21193 Arxiv:2603.02041 Base model:google/gemma-3-4b-p... Base model:quantized:google/ge... Continued-pretraining Conversational Dataset:huggingfacefw/fineweb-... Dataset:taltechnlp/errnews Dataset:taltechnlp/estqa Dataset:taltechnlp/grammar et Dataset:taltechnlp/inflection ... Dataset:taltechnlp/word meanin... Dataset:tartunlp/magpie-gemma-... En Endpoints compatible Estonian Et Gemma Gemma3 Gguf Llama.cpp Region:us Safetensors Sharded Summarization Tensorflow

Model Card on HF 🤗: https://huggingface.co/Abdusin/gemma-3-4b-est-v1

Gemma 3 4B Est V1 Parameters and Internals

LLM Name	Gemma 3 4B Est V1
Repository 🤗	https://huggingface.co/Abdusin/gemma-3-4b-est-v1
Base Model(s)	Gemma 3 4B Pt google/gemma-3-4b-pt
Model Size	4b
Required VRAM	8.6 GB
Updated	2026-10-03
Maintainer	Abdusin
Model Type	gemma3
Model Files	5.0 GB: 1-of-2 3.6 GB: 2-of-2
Supported Languages	et en
Model Architecture	Gemma3ForConditionalGeneration
License	gemma
Model Max Length	131072
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Gemma 3 4B Est V1 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 3 4B Est V1

Best Alternatives	Context / RAM	Downloads	Likes
Medgemma 4B It Abliterated	128K / 6.3 GB	13	6
Gemma 3 Glitter 4B	128K / 8.6 GB	334	7
Fallen Gemma3 4B V1	128K / 8.6 GB	13	18
Gemma 3 4B It	0K / 8.6 GB	1855262	1345
Gemma 3 4B It	0K / 8.6 GB	62743	28
Translategemma 4B It	0K / 8.6 GB	38998	793
Vllm Translategemma 4B It	0K / 8.6 GB	319298	14
...on Content Safety Reasoning 4B	0K / 10 GB	8690	29
Nemotron 3 Content Safety	0K / 8.6 GB	1706	18
Medgemma 4B Antihallu	0K / 8.6 GB	10	0

Note: green Score (e.g. "73.2") means that the model is better than Abdusin/gemma-3-4b-est-v1.