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

Gemma 4 31B It requires approximately 62.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Gemma 4 31B It is developed by google, a model with 31b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Gemma 4 31B It perform on standard benchmarks?

Gemma 4 31B It has the following published scores: LMSYS ELO 1451. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 4 31B It by google — VRAM 62.6GB

Name: Gemma 4 31B It
Author: google

Gemma 4 31B It is an open-source language model by google. Features: 31b LLM, VRAM: 62.6GB, License: apache-2.0, LLM Explorer Score: 0.64, ELO: 1451.

Base model:finetune:google/gem... Base model:google/gemma-4-31b Deploy:azure Endpoints compatible Eval-results Image-text-to-text Region:us Safetensors Sharded Tensorflow

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

Gemma 4 31B It Benchmarks

LMSys ELO 1451 vs 1272 (so35) 14.1%

^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 31B It Parameters and Internals

LLM Name	Gemma 4 31B It
Repository 🤗	https://huggingface.co/google/gemma-4-31B-it
Base Model(s)	Gemma 4 31B google/gemma-4-31B
Model Size	31b
Required VRAM	62.6 GB
Updated	2026-05-26
Maintainer	google
Model Type	gemma4
Model Files	49.8 GB: 1-of-2 12.8 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 It 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

Quantized Models of the Gemma 4 31B It

Model	Likes	Downloads	VRAM
Gemma 4 31B It GGUF	551	486193	1 GB
Gemma 4 31B It AWQ 4bit	51	265351	20 GB
...emma 4 31B It Unsloth Bnb 4bit	22	313172	19 GB
Gemma 4 31B It 4bit	46	45067	18 GB
... 4 31B It Qat Q4 0 Unquantized	39	9972	62 GB
Gemma4 31B 1bit	1	759	3 GB
... 4 31B It Qat Q4 0 Unquantized	4	2074	62 GB
Gemma 4 31B It 8bit	17	3214	33 GB
Gemma 4 31B It UD MLX 4bit	28	792	23 GB
Gemma 4 31B It MLX 8bit	15	972	33 GB

Best Alternatives to Gemma 4 31B It

Best Alternatives	Context / RAM	Downloads	Likes
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
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 NVFP4	0K / 24.8 GB	39440	31
Gemma 4 31B It Abliterated	0K / 62.5 GB	751355	24
Gemma 4 31B It FP8 Dynamic	0K / 33.3 GB	225522	23