LLM EXPLORER 65,695 MODELS INDEXED

NVIDIA Nemotron 3.5 Bolt E4B BF16 by nvidia

By nvidia · 3418 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3.5 Bolt E4B BF16 is an open-source language model by nvidia. Features: 8b LLM, VRAM: 15.9GB, License: other, LLM Explorer Score: 0.38.

  Arxiv:2509.04292   Ar Base model:finetune:google/gem... Base model:google/gemma-4-e4b-...   Bg   Conversational   Cs   Da Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   El   En   Endpoints compatible   Es   Et   Fi   Fr   Gemma4   Hi   Hr   Hu   Id   Image-text-to-text   It   Ja   Ko   Lt   Lv   Nemotron-3.5   Nl   No   Nvidia   Pl   Pt   Pytorch   Region:us   Ro   Ru   Safetensors   Sharded   Sk   Sl   Sv   Tensorflow   Th   Tr   Uk   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 

NVIDIA Nemotron 3.5 Bolt E4B BF16 Parameters and Internals

LLM NameNVIDIA Nemotron 3.5 Bolt E4B BF16
Repository 🤗https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 
Base Model(s)  Gemma 4 E4B It   google/gemma-4-E4B-it
Model Size8b
Required VRAM15.9 GB
Updated2026-10-26
Maintainernvidia
Model Typegemma4
Model Files  15.9 GB: 1-of-1   0.1 GB
Supported Languagesen ar bg cs da de el es et fi fr hi hr hu id it ja ko lt lv nl pl pt ro ru sk sl sv th tr uk vi zh
Model ArchitectureGemma4ForConditionalGeneration
Licenseother
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to NVIDIA Nemotron 3.5 Bolt E4B BF16

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 E4B It0K / 16 GB63279951114
Gemma 4 E4B It0K / 16 GB22990823
Gemma 4 E4B0K / 16 GB268109386
Lite OmniJev0K / 32.1 GB1841
Vishwamai Stage10K / 16 GB4720
Linne Sprout 1 00K / 16 GB351
Gemma 4 E4B It FP8 Dynamic0K / 12 GB311
Gemma4 E4B 8B Heretic Ultra0K / 16 GB980
Gemma E4B Mt B Split30K / 16 GB980
Vishwamai Merged Gemma0K / 16 GB490
Note: green Score (e.g. "73.2") means that the model is better than nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16.