What are the hardware requirements for Nemotron TwoTower 30B A3B Base BF16?

Nemotron TwoTower 30B A3B Base BF16 requires approximately 127.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nemotron TwoTower 30B A3B Base BF16 and how large is it?

Nemotron TwoTower 30B A3B Base BF16 is developed by nvidia, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nemotron TwoTower 30B A3B Base BF16?

Nemotron TwoTower 30B A3B Base BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron TwoTower 30B A3B Base BF16 by nvidia — VRAM 127.1GB, 256K context

Name: Nemotron TwoTower 30B A3B Base BF16
Author: nvidia

Nemotron TwoTower 30B A3B Base BF16 is an open-source language model by nvidia. Features: 30b LLM, VRAM: 127.1GB, Context: 256K, License: other, LLM Explorer Score: 0.23.

Ar Da Dataset:nvidia/nemotron-cc-cod... Dataset:nvidia/nemotron-cc-mat... Dataset:nvidia/nemotron-cc-v2 Dataset:nvidia/nemotron-cc-v2.... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... De Diffusion En Endpoints compatible Es Fr It Ja Ko Mamba Nl Nvidia Pl Pt Pytorch Region:us Ru Safetensors Sharded Sv Tensorflow Th Two-tower Zh

Model Card on HF 🤗: https://huggingface.co/nvidia/Nemotron-TwoTower-30B-A3B-Base-BF16

Nemotron TwoTower 30B A3B Base BF16 Parameters and Internals

LLM Name	Nemotron TwoTower 30B A3B Base BF16
Repository 🤗	https://huggingface.co/nvidia/Nemotron-TwoTower-30B-A3B-Base-BF16
Model Size	30b
Required VRAM	127.1 GB
Updated	2026-06-25
Maintainer	nvidia
Model Type	nemotron_h
Model Files	5.4 GB: 1-of-24 5.4 GB: 2-of-24 5.4 GB: 3-of-24 5.4 GB: 4-of-24 5.4 GB: 5-of-24 5.4 GB: 6-of-24 5.4 GB: 7-of-24 5.4 GB: 8-of-24 5.4 GB: 9-of-24 5.4 GB: 10-of-24 5.4 GB: 11-of-24 5.3 GB: 12-of-24 5.4 GB: 13-of-24 5.4 GB: 14-of-24 5.4 GB: 15-of-24 5.4 GB: 16-of-24 5.4 GB: 17-of-24 5.4 GB: 18-of-24 5.4 GB: 19-of-24 5.4 GB: 20-of-24 5.4 GB: 21-of-24 5.4 GB: 22-of-24 5.4 GB: 23-of-24 3.0 GB: 24-of-24
Supported Languages	en es fr de ja it pt zh ar da ko nl pl ru sv th
Model Architecture	NemotronHTwoTowerForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	131072

Rank the Nemotron TwoTower 30B A3B Base BF16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Nemotron TwoTower 30B A3B Base BF16

Best Alternatives	Context / RAM	Downloads	Likes
...abs TwoTower 30B A3B Base BF16	256K / 127.1 GB	4397	137

Note: green Score (e.g. "73.2") means that the model is better than nvidia/Nemotron-TwoTower-30B-A3B-Base-BF16.