Nemotron 3 Ultra beats open-weight benchmarks

NVIDIA's 550B parameter model (55B active) scores 48 on Artificial Analysis Intelligence Index, serving 300+ tokens/second—a quantized open-weight baseline worth evaluating against proprietary alternatives.

June 3, 2026

Summary

Developers building cost-sensitive inference pipelines now have a verified open-weight option with published throughput metrics. Reduces lock-in pressure for teams benchmarking against closed models.

Why it matters

Developers building cost-sensitive inference pipelines now have a verified open-weight option with published throughput metrics. Reduces lock-in pressure for teams benchmarking against closed models.

Implementation verdict

Replaces proprietary model experimentation for vision-language tasks in resource-constrained deployments. Requires NVFP4 quantization support and Deep Infra or self-hosted inference infrastructure. Worth testing now if you're currently evaluating frontier models.

Sources

  1. 1.550B parameters (55B active)
  2. 2.scores 48 on the Artificial Analysis Intelligence Index
  3. 3.well ahead of the next strongest model, Gemma 4 31B, which scored 39
  4. 4.serves over 300 tokens per second on a pre-release Deep Infra endpoint

Dev Signal

Get briefs like this in your inbox — free, 3x a week.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.