Llama Nemotron Super 49B v1.5 (Non-reasoning)

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Llama Nemotron Super 49B v1.5 Non reasoning by NVIDIA: Text model; TTFT 0.543s, 46.6 tok/s.

Input Modality

Output Modality

Inference Speed

46.586 tokens/s

Latest Release Date

7/25/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Llama Nemotron Super 49B v1.5 (Non-reasoning)

Release date

7/25/2025

Performance

46.586 tokens/s

model_creator.name

NVIDIA

AA Evaluation Scores

AA Intelligence Index

14.6

AA Coding Index

10.5

AA Math Index

MMLU Pro

0.692

GPQA

0.481

HLE

0.043

LiveCodeBench

0.29

SciCode

0.238

Math-500

0.77

AIME

0.137

AIME 2025

0.08

IFBench

0.329

LCR

0.22

TerminalBench Hard

0.038

TAU2

0.251

Output Speed (tokens/s)

46.586 tok/s

TTFT (s)

0.543s

First Answer Token (s)

0.543s

NVIDIA

◎

Llama Nemotron Super 49B v1.5 (Non-reasoning)

$0.10/M$0.40/M

Llama Nemotron Super 49B v1.5 Non reasoning by NVIDIA: Text model; TTFT 0.543s, 46.6 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0