HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Nemotron-3-Content-Safety

nvidia/Nemotron-3-Content-Safety

kind
original
quant
bf16 (16-bit)
family
nemotron
modality
image-text-to-text
root model
google/gemma-3-4b-it
provider
nvidia
license
other
language
en, ar, de, es, fr, hi, ja, th, nl, it, ko, zh
context
128K
library
transformers
vRAM (GB)
—
size on disk
—
downloads
1,252
likes
18
created
—
last modified
2026-06-11T18:29:42+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Nemotron-3-Content-Safety
tags
transformerssafetensorsgemma3image-text-to-textconversationalenardeesfrhijathnlitkozhbase_model:google/gemma-3-4b-itbase_model:finetune:google/gemma-3-4b-itlicense:othertext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
DocVQAmultimodal5.8DocVQAmedium| DocVQA | 5188 | 0.058 |
MMMUmultimodal2.3MMMUmedium| MMMU | 10500 | 0.023 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.