LLM EXPLORER 57,252 MODELS INDEXED

Grug 12B by kai-os

By kai-os · 519 downloads
HF Repo ↗ Copy URL

Grug 12B is an open-source language model by kai-os. Features: 12b LLM, VRAM: 23.9GB, License: other, Instruction-Based, LLM Explorer Score: 0.32.

Base model:finetune:google/gem... Base model:google/gemma-4-12b-...   Compact-reasoning   Conversational Dataset:cl-from-nothing/code r...   Dataset:hotdogs/uka-glm-5.2 Dataset:hsh-intelligence/verif... Dataset:kd13/codedebug-instruc... Dataset:madarabr/cortex-adapti... Dataset:samcheng0/lumia-reason... Dataset:scale-or-reason/genera...   Endpoints compatible   Finetuned   Gemma-4   Gemma4 unified   Image-text-to-text   Instruct   Model-index   Qlora   Reasoning   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kai-os/Grug-12B 

Grug 12B Parameters and Internals

LLM NameGrug 12B
Repository 🤗https://huggingface.co/kai-os/Grug-12B 
Base Model(s)  Gemma 4 12B It   google/gemma-4-12B-it
Model Size12b
Required VRAM23.9 GB
Updated2026-08-09
Maintainerkai-os
Model Typegemma4_unified
Instruction-BasedYes
Model Files  3.9 GB: 1-of-7   3.9 GB: 2-of-7   4.0 GB: 3-of-7   4.0 GB: 4-of-7   4.0 GB: 5-of-7   3.9 GB: 6-of-7   0.2 GB: 7-of-7
Model ArchitectureGemma4UnifiedForConditionalGeneration
Licenseother
Transformers Version5.12.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Grug 12B

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 12B It Esper40K / 23.9 GB42210
Gemma 4 12B It Tachibana Agent0K / 23.9 GB823