Persimmon Built on NVIDIA's 550B Nemotron 3 Ultra with Thousands of Blackwell GPUs
niloofar_mire · x · 2026-09-11
Humans& shared training details for Persimmon: the model was mid- and post-trained starting from NVIDIA's 550B-parameter Nemotron 3 Ultra, using thousands of Blackwell-generation GPUs on a cluster the team recently built.
They note this is an early release, with tool use, longer horizons and more still on the roadmap.
More from Infra
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27
- Lam Research: weekly token usage up ~250x in 18 months — Beth_Kindig · 2026-10-27
- AWS shows how to build enterprise agentic retrieval on Bedrock with CDK — AWS ML Blog · 2026-10-27
- Encrypted GPT-2 speedrun challenges FHE inference: best is 3.031 s/token, goal sub-1s — tensorqt · 2026-10-27
- Open-source Latch compiles PyTorch into training megakernels, 2.75x faster on H100 — sguada · 2026-10-27