What are the hardware requirements for Llama 3 3 Nemotron Super 49B V1.5?

Llama 3 3 Nemotron Super 49B V1.5 requires approximately 100.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3 3 Nemotron Super 49B V1.5 and how large is it?

Llama 3 3 Nemotron Super 49B V1.5 is developed by unsloth, a model with 49b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 3 Nemotron Super 49B V1.5 perform on standard benchmarks?

Llama 3 3 Nemotron Super 49B V1.5 has the following published scores: LMSYS ELO 1343. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 3 Nemotron Super 49B V1.5 by unsloth — VRAM 100.2GB, 128K context

Name: Llama 3 3 Nemotron Super 49B V1.5
Author: unsloth

Llama 3 3 Nemotron Super 49B V1.5 is an open-source language model by unsloth. Features: 49b LLM, VRAM: 100.2GB, Context: 128K, License: other, LLM Explorer Score: 0.33, ELO: 1343.

Arxiv:2411.19146 Arxiv:2502.00203 Arxiv:2505.00949 Base model:finetune:nvidia/lla... Base model:nvidia/llama-3 3-ne... Conversational Custom code En Nemotron-nas Nvidia Region:us Safetensors Sharded Tensorflow Unsloth - llama-3 - pytorch

Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-3_3-Nemotron-Super-49B-v1_5

Llama 3 3 Nemotron Super 49B V1.5 Benchmarks

LMSys ELO 1343 vs 1272 (so35) 5.6%

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

What is the LLM Explorer Rank (Score)

Llama 3 3 Nemotron Super 49B V1.5 Parameters and Internals

LLM Name	Llama 3 3 Nemotron Super 49B V1.5
Repository 🤗	https://huggingface.co/unsloth/Llama-3_3-Nemotron-Super-49B-v1_5
Base Model(s)	...ma 3 3 Nemotron Super 49B V1.5 nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Model Size	49b
Required VRAM	100.2 GB
Updated	2026-08-06
Maintainer	unsloth
Model Type	nemotron-nas
Model Files	5.0 GB: 1-of-21 5.0 GB: 2-of-21 5.0 GB: 3-of-21 4.9 GB: 4-of-21 4.7 GB: 5-of-21 5.0 GB: 6-of-21 5.0 GB: 7-of-21 4.7 GB: 8-of-21 4.7 GB: 9-of-21 4.7 GB: 10-of-21 5.0 GB: 11-of-21 5.0 GB: 12-of-21 4.7 GB: 13-of-21 4.7 GB: 14-of-21 4.8 GB: 15-of-21 4.8 GB: 16-of-21 4.9 GB: 17-of-21 4.7 GB: 18-of-21 4.7 GB: 19-of-21 4.7 GB: 20-of-21 3.5 GB: 21-of-21
Supported Languages	en
Model Architecture	DeciLMForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.54.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 3 Nemotron Super 49B V1.5 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

Quantized Models of the Llama 3 3 Nemotron Super 49B V1.5

Model	Likes	Downloads	VRAM
...motron Super 49B V1.5 Mlx 4Bit	3	368	27 GB

Best Alternatives to Llama 3 3 Nemotron Super 49B V1.5

Best Alternatives	Context / RAM	Downloads	Likes
... Nemotron Super 49B V1.5 NVFP4	128K / 31.1 GB	22695	20
...lama 3 3 Nemotron Super 49B V1	128K / 100.2 GB	189371	325
...lama 3 3 Nemotron Super 49B V1	128K / 100.2 GB	50	0
... 3 Nemotron Super 49B V1.5 FP8	128K / 52 GB	255666	28
...ma 3 3 Nemotron Super 49B V1.5	128K / 100.2 GB	57679	234
Valkyrie 49B V2.1	128K / 100.2 GB	223	30
Valkyrie 49B V2	128K / 100.2 GB	10	30
... 3 3 Nemotron Super 49B V1 FP8	128K / 52 GB	1025	13
...n Super 49B GenRM Multilingual	128K / 99.7 GB	81	7
...a 3 3 Nemotron Super 49B GenRM	128K / 99.7 GB	40	19

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-3_3-Nemotron-Super-49B-v1_5.