LLM EXPLORER 59,962 MODELS INDEXED

Gemma 4 31B Loki Scotoma V2.0 Swa 4096 by CrucibleLab

By CrucibleLab · 37 downloads
HF Repo ↗ Copy URL

Gemma 4 31B Loki Scotoma V2.0 Swa 4096 is an open-source language model by CrucibleLab. Features: 31b LLM, VRAM: 62.5GB, License: apache-2.0, LLM Explorer Score: 0.3.

Base model:finetune:readyart/g... Base model:readyart/gemma-4-31...   Creative-writing   Gemma   Gemma4   Region:us   Roleplay   Safetensors   Sharded   Storywriting   Swa-4096   Tensorflow
Model Card on HF 🤗: https://huggingface.co/CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096 

Gemma 4 31B Loki Scotoma V2.0 Swa 4096 Parameters and Internals

LLM NameGemma 4 31B Loki Scotoma V2.0 Swa 4096
Repository 🤗https://huggingface.co/CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096 
Base Model(s)  Gemma 4 31B It Scotoma 2   ReadyArt/gemma-4-31B-it-scotoma-2
Model Size31b
Required VRAM62.5 GB
Updated2026-08-30
MaintainerCrucibleLab
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>

Best Alternatives to Gemma 4 31B Loki Scotoma V2.0 Swa 4096

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 NVFP40K / 24.8 GB3944031
Gemma 4 31B It Abliterated0K / 62.5 GB75135524
Note: green Score (e.g. "73.2") means that the model is better than CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096.