Nemotron 3.5 Super teased: 120B model with 12B active fits on one DGX Spark, 2.34x Qwen throughput
kuchaev · x · 2026-10-15
A repost claims NVIDIA is releasing Nemotron 3.5 Super VL (120B total, 12B active) that fits on a single DGX Spark, with more models shipping the same day. The attached benchmark chart shows it trading wins with Qwen3.5 122B-A10B, GLM-5.3 Flash and others across SWE-bench Multilingual, Terminal-Bench and BrowseComp, scoring 91.2 on GPQA Diamond, and hitting 4331.88 TPS output on GB200 — 2.34x Qwen3.5. Unconfirmed until official release.
Related event: NVIDIA Launches Nemotron 3.5: Super 120B and Lightning 30B Dual Models(5 posts)→
More from Infra
- Temporal Serverless Workers on Cloud Run: queue-driven autoscaling, scale to zero — rseroter · 2026-10-16
- LMA brings day-0 model support to TPU for the first time, spanning NVIDIA, AMD, Intel via SGLang — ying11231 · 2026-10-16
- Semtech's analyst-day slide cleanly explains the four signal-integrity impairments — BenBajarin · 2026-10-16
- Fortytwo Engine boosts Qwen3.8-27B accuracy 7% and cuts tokens 25% via Swarm Inference — rohanpaul_ai · 2026-10-16
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Robotics data tokenization landscape: Khala maps peaq, THOR, BitRobot and Axis — 0xSammy · 2026-10-16