Llama 3_3 Nemotron Super 49B V1_5
NVIDIA's Llama 3_3 Nemotron Super 49B V 1_5 FP 8 is a large language model exceling at reasoning and text generation tasks, with a notable ability to handle a context window of 131,072 tokens. Its Neural Architecture Search approach enables a desirable balance between model accuracy and efficiency, allowing for larger workloads and deployment on a single GPU. The model demonstrates particular strength in math-related tasks, as evidenced by its top 10% score on the MATH-500 benchmark and top 25% score on the AIME benchmark.
Input
Output
Context
131K
Max Output
66K
Parameters
49.9B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Resources & Links
Estimated GPU requirements for Llama 3_3 Nemotron Super 49B V1_5
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by NVIDIA
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Llama 3_3 Nemotron Super 49B V1_5
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Llama 3_3 Nemotron Super 49B V1_5 advertises a context window of 131,072 tokens, with a maximum output of 65,536 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. Llama 3_3 Nemotron Super 49B V1_5 is an open-weight model released under the Other license, so the weights can be downloaded and self-hosted within that license's terms.
Llama 3_3 Nemotron Super 49B V1_5 accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
Llama 3_3 Nemotron Super 49B V1_5 has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured Llama 3_3 Nemotron Super 49B V1_5 is shown as not available rather than estimated.
Not on the managed pool today; Llama 3_3 Nemotron Super 49B V1_5 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 48.8 GB at INT8 for the weights and a default context, from the catalog's 49.9B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Aug 28, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.