What are the hardware requirements for Arm Gemma E4b?

Arm Gemma E4b requires approximately 17.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Arm Gemma E4b and how large is it?

Arm Gemma E4b is developed by COPA-AI, 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.

Where can I download or evaluate Arm Gemma E4b?

Arm Gemma E4b is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Arm Gemma E4b by COPA-AI — VRAM 17.2GB

Name: Arm Gemma E4b
Author: COPA-AI

Arm Gemma E4b is an open-source language model by COPA-AI. Features: 8.6b LLM, VRAM: 17.2GB, License: gemma, LLM Explorer Score: 0.27.

Arxiv:2609.03350 Armenian Continued-pretraining Dataset:copa-ai/armstem Dataset:copa-ai/armweb En Gemma4 Hy Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/COPA-AI/arm-gemma-e4b

Arm Gemma E4b Parameters and Internals

LLM Name	Arm Gemma E4b
Repository 🤗	https://huggingface.co/COPA-AI/arm-gemma-e4b
Base Model(s)	google/gemma-4-e4b google/gemma-4-e4b
Model Size	8.6b
Required VRAM	17.2 GB
Updated	2026-10-21
Maintainer	COPA-AI
Model Type	gemma4
Model Files	8.9 GB: 1-of-3 5.4 GB: 2-of-3 2.9 GB: 3-of-3
Supported Languages	hy en
Model Architecture	Gemma4ForConditionalGeneration
License	gemma
Transformers Version	5.15.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Arm Gemma E4b 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 Arm Gemma E4b

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E4B It Qat W4a16 Ct	0K / 11.5 GB	292109	27
...emma 4 E4B It GPTQ Safetensors	0K / 10.1 GB	30	0

Note: green Score (e.g. "73.2") means that the model is better than COPA-AI/arm-gemma-e4b.