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

Gemma 4 31B It GGUF requires approximately 1.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Gemma 4 31B It GGUF is developed by unsloth, 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 GGUF perform on standard benchmarks?

Gemma 4 31B It GGUF has the following published scores: LMSYS ELO 1452. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 4 31B It GGUF by unsloth — VRAM 1.2GB

Name: Gemma 4 31B It GGUF
Author: unsloth

Gemma 4 31B It GGUF is an open-source language model by unsloth. Features: 31b LLM, VRAM: 1.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.64, ELO: 1452.

Base model:google/gemma-4-31b-... Base model:quantized:google/ge... Conversational Endpoints compatible Gemma Gemma4 Gguf Google Image-text-to-text Imatrix Q3 Quantized Region:us Unsloth

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

Gemma 4 31B It GGUF Benchmarks

LMSys ELO: 1452 vs 1272 (so35)^14.2%

LLME Score: 0.63557

^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 GGUF (unsloth/gemma-4-31B-it-GGUF)

🌟 Advertise your project 🚀

Gemma 4 31B It GGUF Parameters and Internals

LLM Name	Gemma 4 31B It GGUF
Repository 🤗	https://huggingface.co/unsloth/gemma-4-31B-it-GGUF
Base Model(s)	Gemma 4 31B It google/gemma-4-31B-it
Model Size	31b
Required VRAM	1.2 GB
Updated	2026-06-10
Maintainer	unsloth
Model Type	gemma4
Model Files	17.3 GB 16.4 GB 14.7 GB 13.2 GB 17.3 GB 19.1 GB 18.3 GB 17.4 GB 21.7 GB 21.1 GB 25.2 GB 32.6 GB 10.8 GB 8.5 GB 11.8 GB 11.8 GB 15.4 GB 18.8 GB 21.9 GB 27.5 GB 35.0 GB 1.2 GB 1.2 GB 2.3 GB
GGUF Quantization	Yes
Quantization Type	gguf\|q3\|q4_k\|q5_k
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Torch Data Type	bfloat16

Best Alternatives to Gemma 4 31B It GGUF

Best Alternatives	Context / RAM	Downloads	Likes
...emma 4 31B It Unsloth Bnb 4bit	0K / 19.2 GB	584038	18
Gemma 4 31B It PolarQuant Q5	0K / 21.4 GB	982	3
Gemma 4 31B It Mlx 4bit	0K / 18.5 GB	226	4
Gemma 4 31B It HLWQ Q5	0K / 21.4 GB	8	4
Gemma 4 31B It	0K / 62.6 GB	10706625	2780
Gemma 4 31B IT NVFP4	0K / 32.6 GB	2456814	501
Gemma 4 31B It	0K / 62.6 GB	31809	20
G4 MeroMero 31B	0K / 62.6 GB	3467	55
Equinox 31B	0K / 62.6 GB	506	44
Gemma 4 31B It Heretic	0K / 62.5 GB	12661	51

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

Rank the Gemma 4 31B It GGUF Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 54415 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Gemma 4 31B It GGUF by unsloth

» All LLMs » unsloth » Gemma 4 31B It GGUF URL Share it on

Gemma 4 31B It GGUF Benchmarks

Gemma 4 31B It GGUF Parameters and Internals

Best Alternatives to Gemma 4 31B It GGUF

Rank the Gemma 4 31B It GGUF Capabilities

What open-source LLMs or SLMs are you in search of? 54415 in total.