LLM EXPLORER 56,604 MODELS INDEXED

Gemma 4 31B It MXFP4 by amd

By amd · 370 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It MXFP4 is an open-source language model by amd. Features: 31b LLM, VRAM: 19.5GB, License: apache-2.0.

  8-bit Base model:google/gemma-4-31b-... Base model:quantized:google/ge...   Conversational   Endpoints compatible   Gemma4   Image-text-to-text   Quark   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/amd/gemma-4-31B-it-MXFP4 

Gemma 4 31B It MXFP4 Parameters and Internals

LLM NameGemma 4 31B It MXFP4
Repository 🤗https://huggingface.co/amd/gemma-4-31B-it-MXFP4 
Base Model(s)  Gemma 4 31B It   google/gemma-4-31B-it
Model Size31b
Required VRAM19.5 GB
Updated2026-08-09
Maintaineramd
Model Typegemma4
Model Files  19.5 GB
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0
Tokenizer ClassGemmaTokenizer
Padding Token<eos>

Best Alternatives to Gemma 4 31B It MXFP4

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 31B It Scotoma 20K / 62.5 GB22138
Gemma 4 31B It Abliterated0K / 62.5 GB75135524
Gemma 4 31B StyleTune0K / 65.4 GB230582
Gemma 4 Novelist Eclipse 31B0K / 62.6 GB68936
Gemma 4 31B It Heretic0K / 62.5 GB554163
...sing Calibration 1.5 31B NVFP40K / 20.5 GB4811
Pantheon Reasoning 31B 1.10K / 65.4 GB29420
Note: green Score (e.g. "73.2") means that the model is better than amd/gemma-4-31B-it-MXFP4.