LLM EXPLORER 59,358 MODELS INDEXED

NVIDIA Nemotron 3 Nano 30B A3B BF16 by nvidia

By nvidia · 1645889 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron 3 Nano 30B A3B BF16 is an open-source language model by nvidia. Features: 30b LLM, VRAM: 63.2GB, Context: 256K, License: other, Instruction-Based, LLM Explorer Score: 0.51, ELO: 1315.

  Arxiv:2512.20848   Arxiv:2512.20856   Conversational   Custom code Dataset:nvidia/nemotron-3-nano... Dataset:nvidia/nemotron-agenti... Dataset:nvidia/nemotron-cc-cod... Dataset:nvidia/nemotron-cc-mat...   Dataset:nvidia/nemotron-cc-v2 Dataset:nvidia/nemotron-cc-v2.... Dataset:nvidia/nemotron-compet... Dataset:nvidia/nemotron-instru... Dataset:nvidia/nemotron-math-p... Dataset:nvidia/nemotron-math-v... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-scienc...   De   Deploy:azure   En   Endpoints compatible   Es   Eval-results   Fr   Instruct   It   Ja   Nemotron h   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 

NVIDIA Nemotron 3 Nano 30B A3B BF16 Benchmarks

LMSys ELO 1315 vs 1272 (so35) 3.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

NVIDIA Nemotron 3 Nano 30B A3B BF16 Parameters and Internals

LLM NameNVIDIA Nemotron 3 Nano 30B A3B BF16
Repository 🤗https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 
Model Size30b
Required VRAM63.2 GB
Updated2026-06-05
Maintainernvidia
Model Typenemotron_h
Instruction-BasedYes
Model Files  5.0 GB: 1-of-13   5.0 GB: 2-of-13   5.0 GB: 3-of-13   5.0 GB: 4-of-13   5.0 GB: 5-of-13   5.0 GB: 6-of-13   5.0 GB: 7-of-13   5.0 GB: 8-of-13   5.0 GB: 9-of-13   5.0 GB: 10-of-13   5.0 GB: 11-of-13   5.0 GB: 12-of-13   3.2 GB: 13-of-13
Supported Languagesen es fr de ja it
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.55.4
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Quantized Models of the NVIDIA Nemotron 3 Nano 30B A3B BF16

Model
Likes
Downloads
VRAM
...motron 3 Nano 30B A3B MLX 4Bit120517 GB
...motron 3 Nano 30B A3B MLX 6Bit214825 GB
...A Nemotron 3 Nano 30B A3B 4bit472817 GB
...motron 3 Nano 30B A3B MLX 8Bit223933 GB

Best Alternatives to NVIDIA Nemotron 3 Nano 30B A3B BF16

Best Alternatives
Context / RAM
Downloads
Likes
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB15688
...IA Nemotron 3 Nano 30B A3B FP8256K / 32.7 GB566152356
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB765499174
Nemotron 3 Nano 30B A3B256K / 63.2 GB17431514
... Nemotron 3 Nano 30B A3B NVFP4256K / 19.3 GB200215
...otron 3 Nano 30B A3B MLX MXFP4256K / 16.8 GB6043
...on 3 Nano 30B A3B BF16 Heretic256K / 63.2 GB212
...motron 3 Nano 30B A3B MLX BF16256K / 62.9 GB4440
Nemotron 3 Nano 30B A3B FP8256K / 32.7 GB817
...motron 3 Nano 30B A3B MLX 4Bit256K / 17.8 GB2051