What are the hardware requirements for Gemma 3 4B It Qat Q4 0 Unquantized?

Gemma 3 4B It Qat Q4 0 Unquantized 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 It Qat Q4 0 Unquantized and how large is it?

Gemma 3 4B It Qat Q4 0 Unquantized is developed by google, a model with 4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Gemma 3 4B It Qat Q4 0 Unquantized perform on standard benchmarks?

Gemma 3 4B It Qat Q4 0 Unquantized has the following published scores: LMSYS ELO 1303. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 3 4B It Qat Q4 0 Unquantized by google — VRAM 8.6GB

Name: Gemma 3 4B It Qat Q4 0 Unquantized
Author: google

Gemma 3 4B It Qat Q4 0 Unquantized is an open-source language model by google. Features: 4b LLM, VRAM: 8.6GB, License: gemma, Quantized, LLM Explorer Score: 0.32, ELO: 1303.

Arxiv:1705.03551 Arxiv:1810.12440 Arxiv:1903.00161 Arxiv:1904.09728 Arxiv:1905.07830 Arxiv:1905.10044 Arxiv:1907.10641 Arxiv:1908.02660 Arxiv:1910.11856 Arxiv:1911.01547 Arxiv:1911.11641 Arxiv:2009.03300 Arxiv:2103.03874 Arxiv:2104.12756 Arxiv:2106.03193 Arxiv:2107.03374 Arxiv:2108.07732 Arxiv:2110.14168 Arxiv:2203.10244 Arxiv:2210.03057 Arxiv:2304.06364 Arxiv:2311.12022 Arxiv:2311.16502 Arxiv:2312.11805 Arxiv:2404.12390 Arxiv:2404.16816 Arxiv:2502.12404 Arxiv:2502.21228 Base model:finetune:google/gem... Base model:google/gemma-3-4b-i... Conversational Endpoints compatible Gemma Gemma3 Google Image-text-to-text Q4 Q4 0 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-unquantized

Gemma 3 4B It Qat Q4 0 Unquantized Benchmarks

LMSys ELO 1303 vs 1272 (so35) 2.4%

^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 3 4B It Qat Q4 0 Unquantized Parameters and Internals

LLM Name	Gemma 3 4B It Qat Q4 0 Unquantized
Repository 🤗	https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-unquantized
Base Model(s)	Gemma 3 4B It google/gemma-3-4b-it
Model Size	4b
Required VRAM	8.6 GB
Updated	2026-08-09
Maintainer	google
Model Type	gemma3
Model Files	5.0 GB: 1-of-2 3.6 GB: 2-of-2
Quantization Type	q4\|q4_0
Model Architecture	Gemma3ForConditionalGeneration
License	gemma
Transformers Version	4.52.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Gemma 3 4B It Qat Q4 0 Unquantized 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 3 4B It Qat Q4 0 Unquantized

Model	Likes	Downloads	VRAM
Gemma 3 4B It Qat Abliterated	5	19	15 GB

Best Alternatives to Gemma 3 4B It Qat Q4 0 Unquantized

Best Alternatives	Context / RAM	Downloads	Likes
...4B It 4bit Immersive Translate	0K / 2.2 GB	1338	10
Translategemma 4B It 4bit	0K / 2.2 GB	1619	9
Translategemma 4B It 8bit	0K / 4.1 GB	440	5
Medgemma 1.5 4B It 4bit	0K / 3.4 GB	460	3
Medgemma 1.5 4B It 8bit	0K / 5.7 GB	182	2
Medgemma 1.5 4B It 6bit	0K / 4.5 GB	53	2
Gemma 3 4B It 8bit	0K / 5.7 GB	10585	6
Medgemma 4B It 4bit	0K / 3 GB	1539	3
Gemma 3 4B It 4bit	0K / 3.4 GB	3078	8
Medgemma 4B It 8bit	0K / 5.4 GB	84	3