LLM EXPLORER 57,918 MODELS INDEXED

Gemma 4 31B It NVFP4 Turbo by LilaRest

By LilaRest · 665276 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It NVFP4 Turbo is an open-source language model by LilaRest. Features: 31b LLM, VRAM: 19.4GB, License: apache-2.0, LLM Explorer Score: 0.4.

  4-bit Base model:google/gemma-4-31b-... Base model:quantized:google/ge...   Conversational   Deploy:azure   Endpoints compatible   Gemma-4-31b-it   Gemma4   Lighthouse   Model-index   Modelopt   Nvfp4   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/LilaRest/gemma-4-31B-it-NVFP4-turbo 

Gemma 4 31B It NVFP4 Turbo Parameters and Internals

LLM NameGemma 4 31B It NVFP4 Turbo
Repository 🤗https://huggingface.co/LilaRest/gemma-4-31B-it-NVFP4-turbo 
Base Model(s)  Gemma 4 31B It   Gemma 4 31B IT NVFP4   google/gemma-4-31B-it   nvidia/Gemma-4-31B-IT-NVFP4
Model Size31b
Required VRAM19.4 GB
Updated2026-08-02
MaintainerLilaRest
Model Typegemma4
Model Files  6.2 GB: 1-of-4   5.8 GB: 2-of-4   5.8 GB: 3-of-4   1.6 GB: 4-of-4
Model ArchitectureGemma4ForCausalLM
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It NVFP4 Turbo

Best Alternatives
Context / RAM
Downloads
Likes
Forseti 31B It256K / 61.4 GB580