LLM EXPLORER 61,405 MODELS INDEXED

Wanabi Gemma4 31B by kawaimasa

By kawaimasa · 227 downloads
HF Repo ↗ Copy URL

Wanabi Gemma4 31B is an open-source language model by kawaimasa. Features: 31b LLM, VRAM: 62.6GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:google/gem... Base model:google/gemma-4-31b-...   Conversational   Gemma4   Ja   Japanese   Novel-writing   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kawaimasa/Wanabi-Gemma4-31B 

Wanabi Gemma4 31B Parameters and Internals

LLM NameWanabi Gemma4 31B
Repository 🤗https://huggingface.co/kawaimasa/Wanabi-Gemma4-31B 
Base Model(s)  Gemma 4 31B It   google/gemma-4-31B-it
Model Size31b
Required VRAM62.6 GB
Updated2026-07-03
Maintainerkawaimasa
Model Typegemma4
Model Files  4.2 GB: 1-of-15   4.2 GB: 2-of-15   4.2 GB: 3-of-15   4.3 GB: 4-of-15   4.2 GB: 5-of-15   4.2 GB: 6-of-15   4.3 GB: 7-of-15   4.2 GB: 8-of-15   4.3 GB: 9-of-15   4.2 GB: 10-of-15   4.2 GB: 11-of-15   4.2 GB: 12-of-15   4.2 GB: 13-of-15   4.2 GB: 14-of-15   3.5 GB: 15-of-15
Supported Languagesja
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Wanabi Gemma4 31B

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
Orion 26B A4B V1.10K / 51.6 GB18823
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
Note: green Score (e.g. "73.2") means that the model is better than kawaimasa/Wanabi-Gemma4-31B.