LLM EXPLORER 58,744 MODELS INDEXED

Gemma 4 E4B It Qat Q4 0 Unquantized by google

By google · 10950 downloads
HF Repo ↗ Copy URL

Gemma 4 E4B It Qat Q4 0 Unquantized is an open-source language model by google. Features: 7.9b LLM, VRAM: 15.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.43, ELO: 1318.

  Arxiv:2607.02770   Any-to-any Base model:finetune:google/gem... Base model:google/gemma-4-e4b-...   Endpoints compatible   Gemma4   Image-text-to-text   Q4   Q4 0   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-unquantized 

Gemma 4 E4B It Qat Q4 0 Unquantized 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").

Gemma 4 E4B It Qat Q4 0 Unquantized Parameters and Internals

LLM NameGemma 4 E4B It Qat Q4 0 Unquantized
Repository 🤗https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-unquantized 
Base Model(s)  Gemma 4 E4B It   google/gemma-4-E4B-it
Model Size7.9b
Required VRAM15.9 GB
Updated2026-08-10
Maintainergoogle
Model Typegemma4
Model Files  15.9 GB
Quantization Typeq4|q4_0
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.6.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Quantized Models of the Gemma 4 E4B It Qat Q4 0 Unquantized

Model
Likes
Downloads
VRAM
Gemma 4 E4b It Qat OptiQ 4bit628036 GB

Best Alternatives to Gemma 4 E4B It Qat Q4 0 Unquantized

Best Alternatives
Context / RAM
Downloads
Likes
Firehouse Cactus 1.00K / 15.9 GB7360
Quatfit Mini0K / 31.8 GB10747
Gemma 4 E4B It Qat Bf160K / 15.9 GB771