Unverified50% confidenceBenchmarkExact time
Nvidia's official data claims that Nemotron 3.5 Super VL can achieve up to 5 times higher agent throughput on a single GPU than open-source models of the same scale.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
NVIDIA Open-Sources Nemotron 3.5 Super VL: A 120B Multimodal Model Built for Agents
producthuntProductHunt Daily10/16/2026
Related Entities
Related Claims
UnverifiedThe official statement says that at a 100K input length, Nemotron 3.5 Super VL generates about 5 times faster than Inkling Small, with similar intelligence levels.79% similarUnverifiedNemotron 3.5 Super VL has 120 billion total parameters and 12 billion active parameters.75% similarUnverifiedNvidia open-sourced Nemotron 3.5 Super VL on Hugging Face, a 120B-parameter multimodal mixture-of-experts model focused on professional agent scenarios.73% similarUnverifiedNVIDIA used knowledge distillation to compress the capabilities of the Nemotron 3 family (including Ultra) into Nemotron 3.5 Super VL.72% similarUnverifiedThrough full-stack NIM optimization, the concurrent serving capacity of the Nemotron 3 Ultra model has improved by 2.5x.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053271API
curl https://kongchang.com/api/v1/knowledge/claims/1053271MCP
get_claim(id=1053271)