Sold by: NVIDIAÂ
Deployed on AWS
Free Trial
Llama 3.3 Nemotron Super 49B V1.5 is a significantly upgraded version of Llama 3.3 Nemotron Super 49B V1 and is a large language model (LLM) which is a derivative of Meta Llama-3.3-70B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as RAG and tool calling. The model supports a context length of 128K tokens.
Overview
Llama 3.3 Nemotron Super 49B V1.5 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff.
The model underwent a multiphase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Science, and Tool Calling. Additionally, the model went through multiple stages of Reinforcement Learning (RL) including Reward-aware Preference Optimization (RPO) for chat, Reinforcement Learning with Verifiable Rewards (RLVR) for reasoning, and iterative Direct Preference Optimization (DPO) for Tool Calling capability enhancements. The final checkpoint was achieved after merging several RL and DPO checkpoints.
This model is part of the Llama Nemotron Collection. The other model(s) in this family are: Llama-3.1-Nemotron-Nano-4B-v1.1 Llama-3.1-Nemotron-Ultra-253B-v1 This model is ready for commercial use.
Highlights
- **Architecture Type:** Dense decoder-only Transformer model **Network Architecture:** Llama 3.3 70B Instruct, customized through Neural Architecture Search (NAS) Derivative of Meta Llama-3.3-70B-Instruct, using Neural Architecture Search (NAS). The NAS algorithm results in non-standard and non-repetitive blocks. This includes the following: Skip attention: In some blocks, the attention is skipped entirely, or replaced with a single linear layer.
- We utilize a block-wise distillation of the reference model, where for each block we create multiple variants providing different tradeoffs of quality vs. computational complexity, discussed in more depth below. We then search over the blocks to create a model which meets the required throughput and memory (optimized 1x H100-80GB GPU) while minimizing quality degradation. The model undergoes knowledge distillation (KD), with a focus on English single and multi-turn chat.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 30 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.48xlarge Inference (Batch) Recommended | Model inference on the ml.g5.48xlarge instance type, batch mode | $1.00 |
ml.g6e.24xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.24xlarge instance type, real-time mode | $1.00 |
ml.g5.12xlarge Inference (Batch) | Model inference on the ml.g5.12xlarge instance type, batch mode | $1.00 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $1.00 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $1.00 |
ml.g6e.12xlarge Inference (Real-Time) | Model inference on the ml.g6e.12xlarge instance type, real-time mode | $1.00 |
ml.g6e.48xlarge Inference (Real-Time) | Model inference on the ml.g6e.48xlarge instance type, real-time mode | $1.00 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $1.00 |
ml.p4de.24xlarge Inference (Real-Time) | Model inference on the ml.p4de.24xlarge instance type, real-time mode | $1.00 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $1.00 |
Vendor refund policy
No refund.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
initial release of V 1.5
Additional details
Inputs
- Summary
The model accepts JSON requests with parameters on /invocations and /ping APIs that can be used to control the generated text. See examples and field descriptions below.
- Input MIME type
- application/json
{
"model": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"messages": [{"role": "system", "content": "detailed thinking off"}, {"role":"user", "content":"Write a limerick about the wonders of GPU computing."}],
"max_tokens": 64
}
No sample data for Batch job, can use same as above
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
model | Name of the model: nvidia/llama-3_3-nemotron-super-49b-v1_5 | Type: FreeText | No |
messages.role | Role of the entity in conversation | Type: Categorical Allowed values: system, user, assistant | Yes |
max_tokens | Number of tokens that can be generated in the model's response | 1 to 65536. Defaults to 65536 | No |
Resources
Support
Vendor support
Free support via NVIDIA NIM Developer Forum:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
This product has charges associated with it for seller support. Run & Manage latest LLMs locally, privately, securely and cost-effectively without any vendor lock-in. This VM solution comes with GPU support , pre-loaded with LLaMA, Mistral, Gemma, DeepSeek, & Qwen models along with Open-WebUI as an intuitive UI to interact with the LLMs and Ollama to install new models as needed.
This product has charges associated with it for seller support. Run & Manage latest LLMs locally, privately, securely and cost-effectively without any vendor lock-in.
This VM solution comes pre-loaded with LLaMA, Mistral, Gemma, DeepSeek, & Qwen models along with Open-WebUI as an intuitive UI to interact with the LLMs and Ollama to install new models as needed.
This is an OpenAI API compatible repackaged open source product of all new LLaMa 3 Meta AI 70B with optional support from Meetrix.io. With the SSL auto generation and preconfigured OpenAI API, the LLaMa 3 70B AMI is the perfect alternative for costly solutions such as GPT-4. Keep costs low with pay-as-you-go pricing, while gaining access to expert assistance.
This is an OpenAI API compatible single-click deployment AMI package of LLaMa 2 Meta AI 7B which is tailored for the 7 billion parameter pretrained generative text model. This Amazon Machine Image is easily deployable without devops hassle and fully optimized for developers eager to harness the power of advanced text generation capabilities. With the SSL auto generation and preconfigured OpenAI API, the LLaMa 2 7B AMI is the perfect alternative for costly solutions such as ChatGPT.
This is a single-click deployment AMI for Code Llama 34B Instruct, which is an AI model built on top of Llama 2, fine-tuned for generating and discussing code. It is a large language model (LLM) that can use text prompts to generate and discuss code. Code Llama is state-of-the-art for publicly available LLMs on coding tasks. It has the potential to make workflows faster and more efficient for developers and lower the barrier to entry for people who are learning to code. Code Llama has the potential to be used as a productivity and educational tool to help programmers write more robust, well-documented software.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.