Nemotron 3.5 Super VL hits ~630 tokens/s at 100k-token prompts, fastest 20+ score model measured
ArtificialAnlys · x · 2026-10-15
Measured on a pre-release DeepInfra endpoint serving NVFP4 weights, Nemotron 3.5 Super VL reaches 630 tokens/s output at 100k-token prompts — the fastest of any model scoring 20+ on the Intelligence Index that Artificial Analysis has measured at this prompt length.
- 5x Inkling Small (124 tokens/s), 2.7x Nemotron 3 Ultra (235), 4.5x Nemotron 3 Super (140)
- First token in 1.8s, vs 4.4s for Nemotron 3 Ultra and 8.5s for Inkling Small
More from Infra
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16
- Fastino launches Training API for SFT/RL, claiming 25-85% cost cut vs Tinker — kalyan_kpl · 2026-10-16