What are the hardware requirements for Gemma 4 31B It Speculator.eagle3?

Gemma 4 31B It Speculator.eagle3 requires approximately 4.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 31B It Speculator.eagle3 and how large is it?

Gemma 4 31B It Speculator.eagle3 is developed by RedHatAI, a model with 31b 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 Gemma 4 31B It Speculator.eagle3?

Gemma 4 31B It Speculator.eagle3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 31B It Speculator.eagle3 by RedHatAI — VRAM 4.5GB

Name: Gemma 4 31B It Speculator.eagle3
Author: RedHatAI

Gemma 4 31B It Speculator.eagle3 is an open-source language model by RedHatAI. Features: 31b LLM, VRAM: 4.5GB, License: apache-2.0, LLM Explorer Score: 0.3.

Arxiv:2503.01840 Custom code Eagle3 Gemma4 Neuralmagic Redhat Region:us Safetensors Speculators

Model Card on HF 🤗: https://huggingface.co/RedHatAI/gemma-4-31B-it-speculator.eagle3

Gemma 4 31B It Speculator.eagle3 Parameters and Internals

LLM Name	Gemma 4 31B It Speculator.eagle3
Repository 🤗	https://huggingface.co/RedHatAI/gemma-4-31B-it-speculator.eagle3
Model Size	31b
Required VRAM	4.5 GB
Updated	2026-08-01
Maintainer	RedHatAI
Model Files	4.5 GB
Model Architecture	Eagle3DraftModel
License	apache-2.0
Transformers Version	5.5.0

Rank the Gemma 4 31B It Speculator.eagle3 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