LLM EXPLORER 61,836 MODELS INDEXED

Gemma 4 31B It Scotoma 2 by ReadyArt

By ReadyArt · 221 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It Scotoma 2 is an open-source language model by ReadyArt. Features: 31b LLM, VRAM: 62.5GB, License: apache-2.0, LLM Explorer Score: 0.29.

  Conversational   Endpoints compatible   Gemma4   Image-text-to-text   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ReadyArt/gemma-4-31B-it-scotoma-2 

Gemma 4 31B It Scotoma 2 Parameters and Internals

LLM NameGemma 4 31B It Scotoma 2
Repository 🤗https://huggingface.co/ReadyArt/gemma-4-31B-it-scotoma-2 
Base Model(s)  google/gemma-4-31b-it   google/gemma-4-31b-it
Model Size31b
Required VRAM62.5 GB
Updated2026-08-08
MaintainerReadyArt
Model Typegemma4
Model Files  49.9 GB: 1-of-2   12.6 GB: 2-of-2
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.12.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Quantized Models of the Gemma 4 31B It Scotoma 2

Model
Likes
Downloads
VRAM
Gemma 4 31B It Scotoma 2 10bit15040 GB

Best Alternatives to Gemma 4 31B It Scotoma 2

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B It0K / 62.6 GB107066252780
Gemma 4 31B It0K / 62.6 GB3033922
Gemma 4 31B IT NVFP40K / 32.6 GB2773900547
Gemma 4 31B0K / 62.6 GB178519
Gemma 4 31B JANG 4M CRACK0K / 22.6 GB240561704
Gemma 4 31B0K / 62.6 GB694395498
Gemma 4 31B It FP8 Block0K / 33.3 GB379858244
Gemma 4 31B It NVFP40K / 23.3 GB111553957
Gemma 4 31B It Abliterated0K / 62.5 GB75135524
Orion 26B A4B V1.10K / 51.6 GB18823
Note: green Score (e.g. "73.2") means that the model is better than ReadyArt/gemma-4-31B-it-scotoma-2.