NVIDIA logo

Llama 3.3 Nemotron Super 49B

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 3.3 Nemotron Super 49B is NVIDIA's language model. A 49B-parameter compute-efficient LLM fine-tuned by NVIDIA on Llama 3.3, targeting multi-agent and agentic system workloads with the Nemotron Super architecture.
Specifications
Canonical IDnvidia-llama-3-3-nemotron-super-49b
TypeLanguage
StatusActive
CreatorNVIDIANVIDIA
Input ModalitiesText
Output ModalitiesText
Parameters49B
Benchmarks
Intelligence Index
8.5
#335
Math Index
7.7
#229
MMLU-Pro
0.7
#205
GPQA
0.5
#323
HLE
0.0
#454
LiveCodeBench
0.3
#220
AIME
0.2
#94
IFBench
0.4
#243
Time to First Token
0.00s
#182
SciCode
0.2
#338
MATH-500
0.8
#102
AIME 2025
0.1
#229
LCR
0.1
#309
TerminalBench Hard
0.0
#385
Output TPS
0.0
#443

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3.3 Nemotron Super 49B, ranked by cheapest on-demand price. The model needs about 118 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hrwestus2
Standard_NP40sAzure4× AMD Alveo U250 FPGA (64GB)256 GB$6.60/hrwestus2
Standard_NC48ads_A100_v4Azure2× NVIDIA A100160 GB$7.35/hrwestus2
7 more instances can run Llama 3.3 Nemotron Super 49B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama Nemotron 1.5 Super 49B Reasoning————Available
Llama Nemotron 1.5 Super 49B————Available
Llama 3.3 Nemotron Super 49B————Current
Llama 3.3 Nemotron Super 49B Reasoning————Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Llama 3.3 70B Instruct—131K$0.120$0.200
Llama 3.2 3B Instruct—131K$0.015$0.020
Llama 3.2 1B Instruct—131K$0.027$0.080
Llama 3.2 11B—128K$0.160$0.160
Llama 3.1 405B Instruct—131K$0.120$0.300
Llama 3.1 8B Instruct—200K$0.020$0.030
Llama 3.1 70B Instruct—131K$0.120$0.300
Llama 3.1 70B—128K$0.360$0.360
Llama 3.1 8B—131K$0.030$0.050
Llama 3 70B Instruct—131K$0.120$0.300

Model IDs

llama-3-3-nemotron-super-49b
llama-3-3-nemotron-super-49b-reasoning
nvidia-llama-3-3-nemotron-super-49b