What are the hardware requirements for Gemma 4 E4B It GPTQ Safetensors?

Gemma 4 E4B It GPTQ Safetensors requires approximately 10.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Gemma 4 E4B It GPTQ Safetensors is developed by simaai, a model with 8.6b 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 GPTQ Safetensors perform on standard benchmarks?

Gemma 4 E4B It GPTQ Safetensors 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 GPTQ Safetensors by simaai — VRAM 10.1GB

Name: Gemma 4 E4B It GPTQ Safetensors
Author: simaai

Gemma 4 E4B It GPTQ Safetensors is an open-source language model by simaai. Features: 8.6b LLM, VRAM: 10.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.37, ELO: 1318.

Any-to-any Base model:google/gemma-4-e4b-... Base model:quantized:google/ge... Compressed-tensors Endpoints compatible Gemma4 Gptq Image-text-to-text Multilingual Quantized Region:us Rtn Safetensors Sima-ai

Model Card on HF 🤗: https://huggingface.co/simaai/Gemma-4-E4B-it-GPTQ-Safetensors

Gemma 4 E4B It GPTQ Safetensors 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 GPTQ Safetensors Parameters and Internals

LLM Name	Gemma 4 E4B It GPTQ Safetensors
Repository 🤗	https://huggingface.co/simaai/Gemma-4-E4B-it-GPTQ-Safetensors
Base Model(s)	Gemma 4 E4B It google/gemma-4-E4B-it
Model Size	8.6b
Required VRAM	10.1 GB
Updated	2026-10-14
Maintainer	simaai
Model Type	gemma4
Model Files	10.1 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.10.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 E4B It GPTQ Safetensors 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 4 E4B It GPTQ Safetensors

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E4B It Qat W4a16 Ct	0K / 11.5 GB	292109	27
Arm Gemma E4b	0K / 17.2 GB	199	1