What are the hardware requirements for Nemotron 3 Super 64B A12B Math REAP BF16?

Nemotron 3 Super 64B A12B Math REAP BF16 requires approximately 128.6 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 3 Super 64B A12B Math REAP BF16 and how large is it?

Nemotron 3 Super 64B A12B Math REAP BF16 is developed by Max-and-Omnis, a model with 120b 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 3 Super 64B A12B Math REAP BF16?

Nemotron 3 Super 64B A12B Math REAP BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron 3 Super 64B A12B Math REAP BF16 by Max-and-Omnis — VRAM 128.6GB, 256K context

Name: Nemotron 3 Super 64B A12B Math REAP BF16
Author: Max-and-Omnis

Nemotron 3 Super 64B A12B Math REAP BF16 is an open-source language model by Max-and-Omnis. Features: 120b LLM, VRAM: 128.6GB, Context: 256K, License: other, LLM Explorer Score: 0.25.

Arxiv:2512.20856 Aime Aimo Base model:finetune:nvidia/nvi... Base model:nvidia/nvidia-nemot... Conversational Custom code Dataset:nguyen599/astralmath-v... Endpoints compatible Finetuned Latent-moe Mamba2 Math Nemotron-3 Nemotron h Nvidia Pruned Python Pytorch Reap Region:us Safetensors Sharded Tensorflow Tool-integrated reasoning

Model Card on HF 🤗: https://huggingface.co/Max-and-Omnis/Nemotron-3-Super-64B-A12B-Math-REAP-BF16

Nemotron 3 Super 64B A12B Math REAP BF16 Parameters and Internals

LLM Name	Nemotron 3 Super 64B A12B Math REAP BF16
Repository 🤗	https://huggingface.co/Max-and-Omnis/Nemotron-3-Super-64B-A12B-Math-REAP-BF16
Base Model(s)	...emotron 3 Super 120B A12B BF16 nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Model Size	120b
Required VRAM	128.6 GB
Updated	2026-05-30
Maintainer	Max-and-Omnis
Model Type	nemotron_h
Model Files	5.0 GB: 1-of-26 5.0 GB: 2-of-26 5.0 GB: 3-of-26 5.0 GB: 4-of-26 5.0 GB: 5-of-26 5.0 GB: 6-of-26 5.0 GB: 7-of-26 5.0 GB: 8-of-26 5.0 GB: 9-of-26 5.0 GB: 10-of-26 5.0 GB: 11-of-26 5.0 GB: 12-of-26 5.0 GB: 13-of-26 5.0 GB: 14-of-26 4.9 GB: 15-of-26 5.0 GB: 16-of-26 5.0 GB: 17-of-26 5.0 GB: 18-of-26 5.0 GB: 19-of-26 5.0 GB: 20-of-26 5.0 GB: 21-of-26 5.0 GB: 22-of-26 5.0 GB: 23-of-26 5.0 GB: 24-of-26 5.0 GB: 25-of-26 3.7 GB: 26-of-26
Model Architecture	NemotronHForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.5.4
Padding Token	<\|im_end\|>
Vocabulary Size	131072

Rank the Nemotron 3 Super 64B A12B Math REAP 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 3 Super 64B A12B Math REAP BF16

Best Alternatives	Context / RAM	Downloads	Likes
... Nemotron 3.5 Super VL Finance	1024K / 172 GB	2062	11
...motron 3.5 Super VL Healthcare	1024K / 172 GB	2011	10
... Imid Combined Unsafe Midtrain	1024K / 209.5 GB	282	0
Phonellm Max Alpha 2	1024K / 188.5 GB	692	4
... 120B Imid Combined Unsafe Sft	1024K / 209.5 GB	80	0
...3.5 Super VL 120B A12B JANG 4M	1024K / 75.2 GB	369	1
...on 3 Super 120B A12B Base BF16	1024K / 209.5 GB	13053	32
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	3041935	408
...emotron 3 Super 120B A12B BF16	256K / 194.6 GB	864394	414
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	1132	27

Note: green Score (e.g. "73.2") means that the model is better than Max-and-Omnis/Nemotron-3-Super-64B-A12B-Math-REAP-BF16.