NVIDIA cloud models

19 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.

Model	Intelligence	Speed (tok/s)
Nemotron 3 Ultra 550B A55B (Reasoning)	23.4	175.767
Nemotron 3.5 Lightning	13.6	276.957
Nemotron 3 Super 120B A12B (Reasoning)	13.6	105.583
Nemotron Cascade 2 30B A3B	11.7	0
Nemotron 3 Nano Omni 30B A3B Reasoning	10.3	0
Llama Nemotron Super 49B v1.5 (Reasoning)	9	58.706
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)	8.9	231.825
Llama 3.3 Nemotron Super 49B v1 (Reasoning)	8.9	0
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)	7.5	0
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)	7.5	68.502
NVIDIA Nemotron Nano 9B V2 (Reasoning)	7.4	100.118
Llama Nemotron Super 49B v1.5 (Non-reasoning)	7.4	51.119
NVIDIA Nemotron 3 Nano 4B	7.4	0
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)	7.3	0
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)	7.3	0
Llama 3.1 Nemotron Instruct 70B	6.9	63.28
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)	6.8	153.738
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)	6.8	178.472
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)	5.8	72.209

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.