What are the hardware requirements for Gemma 4 31B FP8 Dynamic?

Gemma 4 31B FP8 Dynamic requires approximately 33.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 31B FP8 Dynamic and how large is it?

Gemma 4 31B FP8 Dynamic is developed by axteam, 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 FP8 Dynamic?

Gemma 4 31B FP8 Dynamic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 31B FP8 Dynamic by axteam — VRAM 33.3GB

Name: Gemma 4 31B FP8 Dynamic
Author: axteam

Gemma 4 31B FP8 Dynamic is an open-source language model by axteam. Features: 31b LLM, VRAM: 33.3GB, License: apache-2.0, LLM Explorer Score: 0.3.

Base model:google/gemma-4-31b Base model:quantized:google/ge... Compressed-tensors Endpoints compatible Fp8 Gemma Gemma4 Image-text-to-text Quantized Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/axteam/gemma-4-31B-FP8-dynamic

Gemma 4 31B FP8 Dynamic Parameters and Internals

LLM Name	Gemma 4 31B FP8 Dynamic
Repository 🤗	https://huggingface.co/axteam/gemma-4-31B-FP8-dynamic
Base Model(s)	Gemma 4 31B google/gemma-4-31B
Model Size	31b
Required VRAM	33.3 GB
Updated	2026-10-15
Maintainer	axteam
Model Type	gemma4
Model Files	26.9 GB: 1-of-2 6.4 GB: 2-of-2
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 31B FP8 Dynamic 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 31B FP8 Dynamic

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 31B It	0K / 62.6 GB	10706625	2780
Gemma 4 31B It	0K / 62.6 GB	30339	22
Gemma 4 31B IT NVFP4	0K / 32.6 GB	2773900	547
Gemma 4 31B	0K / 62.6 GB	1785	19
Gemma 4 31B JANG 4M CRACK	0K / 22.6 GB	24056	1704
Gemma 4 31B	0K / 62.6 GB	694395	498
Quyet 1.0 Large	0K / 62.6 GB	1128	42
Gemma 4 31B It FP8 Block	0K / 33.3 GB	3798582	44
Gemma 4 31B It NVFP4	0K / 23.3 GB	1115539	57
Gemma 4 31B It Abliterated	0K / 62.5 GB	751355	24

Note: green Score (e.g. "73.2") means that the model is better than axteam/gemma-4-31B-FP8-dynamic.