LLM EXPLORER 61,491 MODELS INDEXED

Gemma 4 31B It SFT OCR OCR INT8 by lokeshe09

By lokeshe09 · 20 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It SFT OCR OCR INT8 is an open-source language model by lokeshe09. Features: 31b LLM, VRAM: 33.3GB, License: apache-2.0, LLM Explorer Score: 0.29.

  8-bit Base model:lokeshe09/gemma-4-3... Base model:quantized:lokeshe09...   Compressed-tensors   Conversational   Gemma4   Image-text-to-text   Int8   Llmcompressor   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lokeshe09/gemma-4-31B-it-SFT_OCR_OCR-INT8 

Gemma 4 31B It SFT OCR OCR INT8 Parameters and Internals

LLM NameGemma 4 31B It SFT OCR OCR INT8
Repository 🤗https://huggingface.co/lokeshe09/gemma-4-31B-it-SFT_OCR_OCR-INT8 
Base Model(s)  Gemma 4 31B It SFT OCR OCR   lokeshe09/gemma-4-31B-it-SFT_OCR_OCR
Model Size31b
Required VRAM33.3 GB
Updated2026-09-17
Maintainerlokeshe09
Model Typegemma4
Model Files  26.9 GB: 1-of-2   6.4 GB: 2-of-2
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Best Alternatives to Gemma 4 31B It SFT OCR OCR INT8

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
Orion 26B A4B V1.10K / 51.6 GB18823
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 lokeshe09/gemma-4-31B-it-SFT_OCR_OCR-INT8.