What are the hardware requirements for Gemma 4 E4B It AWQ 8bit?

Gemma 4 E4B It AWQ 8bit requires approximately 12.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 E4B It AWQ 8bit and how large is it?

Gemma 4 E4B It AWQ 8bit is developed by axteam, a model with 7.9b 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 AWQ 8bit perform on standard benchmarks?

Gemma 4 E4B It AWQ 8bit 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 AWQ 8bit by axteam — VRAM 12.2GB

Name: Gemma 4 E4B It AWQ 8bit
Author: axteam

Gemma 4 E4B It AWQ 8bit is an open-source language model by axteam. Features: 7.9b LLM, VRAM: 12.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1318.

8bit Awq Base model:google/gemma-4-e4b-... Base model:quantized:google/ge... Compressed-tensors Conversational Endpoints compatible Gemma Gemma4 Image-text-to-text Int8 Quantized Region:us Safetensors Vllm

Model Card on HF 🤗: https://huggingface.co/axteam/gemma-4-E4B-it-AWQ-8bit

Gemma 4 E4B It AWQ 8bit 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 AWQ 8bit Parameters and Internals

LLM Name	Gemma 4 E4B It AWQ 8bit
Repository 🤗	https://huggingface.co/axteam/gemma-4-E4B-it-AWQ-8bit
Base Model(s)	Gemma 4 E4B It google/gemma-4-E4B-it
Model Size	7.9b
Required VRAM	12.2 GB
Updated	2026-10-15
Maintainer	axteam
Model Type	gemma4
Model Files	12.2 GB
AWQ Quantization	Yes
Quantization Type	awq\|8bit
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 E4B It AWQ 8bit 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 AWQ 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E4B It AWQ 4bit	0K / 10.4 GB	31	1
... 4 E4B It Qat Q4 0 Unquantized	0K / 15.9 GB	10950	27
... 4 E4B It Qat Q4 0 Unquantized	0K / 15.9 GB	1285	3
Baihua Gemma4 E4B	0K / 15.9 GB	135	3
Kitsune Tales E4B EN	0K / 15.9 GB	298	1
Kitsune Tales E4B JP	0K / 15.9 GB	289	1
Gemma 4 E4B It NVFP4A16	0K / 10.3 GB	31	1
Gemma 4 E4B It NVFP4	0K / 10.3 GB	31	1
ContextPilot E4B	0K / 15.9 GB	404	5
Firehouse Cactus 1.0	0K / 15.9 GB	736	0

Note: green Score (e.g. "73.2") means that the model is better than axteam/gemma-4-E4B-it-AWQ-8bit.