SAVRN
Search Contact SAVRN

Open-weight model · Any to any

gemma-4-E2B-it

by Google google/gemma-4-E2B-it

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output.

Parameters5.1B
Context131,072
Weights10.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads3.5M

Runs On

What it takes to serve gemma-4-E2B-it (5.1B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 10.2 GB 12.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 5.1 GB 6.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 2.6 GB 3.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on gemma-4-E2B-it

Text, images and audio go in, text comes out, and this instruction-tuned checkpoint runs in 12.3 GB at 16-bit, 6.1 GB at 8-bit, 3.1 GB at 4-bit. On the least expensive card the Index prices for it, a single MI300X at $1.85 an hour on-demand, most of the 192 GB stays free for the 131,072 token window. At 5.1 billion parameters and more than 140 languages, it is sized for one card running multilingual assistants that read pictures and hear speech.

Under Apache 2.0 you can modify, redistribute and sell what you build on it, keeping the license and notice files and stating significant changes, with an express patent grant included. Look at the context figure: the configuration says 131,072 tokens while Google's family description says up to 256K, so confirm which your stack honors. No host prices per million tokens are listed, and its pre-trained base is google/gemma-4-E2B.

SAVRN Research, 2026-09-18

Model Card

By Google, published under apache-2.0, revision 3e22461f65e8.

Hugging Face | GitHub | Launch Blog | Documentation | Technical Report
License: Apache 2.0 | Authors: Google DeepMind

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.

Gemma 4 introduces key capability and architectural advancements:

Read the full model card (3,425 words)

Configuration

Architecture
Gemma4ForConditionalGeneration
Context length (tokens)
131,072
Layers
35
Hidden size
1,536
Feed-forward size
6,144
Attention heads
8
Key/value heads
1
Head dimension
256
Vocabulary size
262,144
Sliding window (tokens)
512
Model type
gemma4

Identity and Version

Repository
google/gemma-4-E2B-it
Publisher
Google
Task
Any to any
Modality
Multimodal
Library
transformers
Parameters
5.1B parameters
Languages
Not stated by the source
Revision
3e22461f65e89153144f8adb70e3b8c2cc9845a7
First published
2026-03-02
Last updated
2026-07-20

Files and Weights

9 files, 10.3 GB in total. The weights are 1 file totalling 10.2 GB in safetensors.

Weights1 file · 10.2 GB
Configuration3 files · 6.9 KB
Tokenizer2 files · 32.2 MB
Documentation1 file · 28.0 KB
Other1 file · 18.6 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights10.2 GB 2db5482b20d7
config.jsonConfiguration5.0 KB —
generation_config.jsonConfiguration208 B —
processor_config.jsonConfiguration1.7 KB —
README.mdDocumentation28.0 KB —
chat_template.jinjaOther18.6 KB —
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer32.2 MB cc8d3a0ce364
tokenizer_config.jsonTokenizer3.1 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
10.2 GB
Download from Google

Released by Google through Kaggle. Read the license.

Built From

Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

BenchmarkConditionsResultReported byRevisionDate
ARTPARK-IISc/Vaani-Benchmark-V1.0 Task Hindi_WERMetric Hindi_WERComparison conditions not established 19.4 Not named
Reported by a third party		 Evaluated revision not stated 2026-06-26
Idavidrein/gpqa Task diamondMetric diamondComparison conditions not established 43.4 Model Card
Reported by a third party		 Evaluated revision not stated 2026-04-02
LiquidAI/ifstruct-v1.0 Task ifstruct_v1Metric ifstruct_v1Comparison conditions not established 64.85 Liquid AI — IFStruct v1.0 blog (gemma-4-E2B-it)
Reported by a third party		 Evaluated revision not stated 2026-06-30
MMMU/MMMU_Pro Task mmmu_pro_visionMetric mmmu_pro_visionComparison conditions not established 44.2 Model Card
Reported by a third party		 Evaluated revision not stated 2026-05-12
MathArena/aime_2026 Task MathArena/aime_2026Metric MathArena/aime_2026Comparison conditions not established 37.5 Model Card
Reported by a third party		 Evaluated revision not stated 2026-03-02
TIGER-Lab/MMLU-Pro Task mmlu_proMetric mmlu_proComparison conditions not established 60 Model Card
Reported by a third party		 Evaluated revision not stated 2026-04-02
llamaindex/ExtractBench Task longMetric longSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 14.58 ExtractBench
Reported by a third party		 Evaluated revision not stated 2026-08-24
llamaindex/ExtractBench Task meanMetric meanSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 51.85 ExtractBench
Reported by a third party		 Evaluated revision not stated 2026-08-24
llamaindex/ExtractBench Task mediumMetric mediumSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 28.96 ExtractBench
Reported by a third party		 Evaluated revision not stated 2026-08-24
llamaindex/ExtractBench Task shortMetric shortSetup Pipeline name: gemma4_e2b_vllm_extract_oneshot_structured_output_fileComparison conditions not established 63.71 ExtractBench
Reported by a third party		 Evaluated revision not stated 2026-08-24

Memory Requirements

PrecisionWeights in memory
As published10.2 GB
16-bit10.2 GB
8-bit5.1 GB
4-bit2.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Built on This Model

Compare gemma-4-E2B-it

Questions About gemma-4-E2B-it

How much GPU memory does gemma-4-E2B-it need?

About 12.3 GB at 16-bit and 3.1 GB at 4-bit: the weights (5.1B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run gemma-4-E2B-it on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use gemma-4-E2B-it commercially?

Yes. gemma-4-E2B-it is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is gemma-4-E2B-it's context length?

131,072 tokens, from the maximum position embeddings in its published configuration.

Similar Models

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 4-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 8-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 6-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model

LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. 5-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon. Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model

Model · Any to any

gemma-4-E2B

Google

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: E2B, E4B, 12B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from…

Open weights apache-2.0 5.1B parameters 131,072 tokens transformers
View model