What are the hardware requirements for Gemma 4 31B It Qat Q4 0 Unquantized?

Gemma 4 31B It Qat Q4 0 Unquantized 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 Qat Q4 0 Unquantized and how large is it?

Gemma 4 31B It Qat Q4 0 Unquantized 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 Qat Q4 0 Unquantized perform on standard benchmarks?

Gemma 4 31B It Qat Q4 0 Unquantized 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 Qat Q4 0 Unquantized by google — VRAM 62.6GB

Name: Gemma 4 31B It Qat Q4 0 Unquantized
Author: google

Gemma 4 31B It Qat Q4 0 Unquantized is an open-source language model by google. Features: 31b LLM, VRAM: 62.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.44, ELO: 1451.

Arxiv:2607.02770 Base model:finetune:google/gem... Base model:google/gemma-4-31b-... Conversational Endpoints compatible Gemma4 Image-text-to-text Q4 Q4 0 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized

Gemma 4 31B It Qat Q4 0 Unquantized 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 Qat Q4 0 Unquantized Parameters and Internals

LLM Name	Gemma 4 31B It Qat Q4 0 Unquantized
Repository 🤗	https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized
Base Model(s)	Gemma 4 31B It google/gemma-4-31B-it
Model Size	31b
Required VRAM	62.6 GB
Updated	2026-08-09
Maintainer	google
Model Type	gemma4
Model Files	49.8 GB: 1-of-2 12.8 GB: 2-of-2
Quantization Type	q4\|q4_0
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.6.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 31B It Qat Q4 0 Unquantized 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 Qat Q4 0 Unquantized

Model	Likes	Downloads	VRAM
Gemma 4 31B It Qat W4a16 Ct	55	2187795	23 GB
Gemma 4 31B It Qat GGUF	175	200029	0 GB
Gemma 4 31B It Qat AWQ INT4	7	313817	20 GB
Gemma 4 31B It Qat W4a16	4	57073	23 GB
Gemma 4 31B It Qat OptiQ 4bit	6	6227	22 GB
...31B It Qat NVFP4 Mse Blackwell	3	440	20 GB
...t Q4 0 Unquantized Abliterated	16	229	62 GB
Couture Engine 31B V1.0 Lora	0	23	0 GB

Best Alternatives to Gemma 4 31B It Qat Q4 0 Unquantized

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 31B It 4bit	0K / 18.5 GB	45067	46
...emma 4 31B It Unsloth Bnb 4bit	0K / 19.2 GB	19306	25
... 4 31B It Qat Q4 0 Unquantized	0K / 62.6 GB	2074	4
Gemma 4 31B It 8bit	0K / 33.8 GB	3214	17
Gemma 4 31B 8bit	0K / 33.8 GB	957	24
Gemma 4 31B It UD MLX 4bit	0K / 23.2 GB	792	28
Gemma 4 31B It MLX 8bit	0K / 33.8 GB	972	15
Gemma 4 31B It 6bit	0K / 26 GB	906	7
Gemma 4 31B 4bit	0K / 18.5 GB	448	11
Gemma 4 31B It Qat W4a16 Ct	0K / 23.3 GB	2187795	55

Note: green Score (e.g. "73.2") means that the model is better than google/gemma-4-31B-it-qat-q4_0-unquantized.