Persimmon Was Mid- and Post-Trained From NVIDIA's 550B Nemotron 3 Ultra on Blackwell GPUs
niloofar_mire · x · 2026-09-11
humans& shared training details for its Persimmon user model: it was mid- and post-trained from NVIDIA's 550B-parameter Nemotron 3 Ultra using thousands of Blackwell-generation GPUs on the startup's own cluster. The team calls it an early release, with tool use and longer-horizon simulation still ahead.
More from Infra
- 1:26 continuous aerial AI video made entirely on a Mac with MiniMax H3 — cocktailpeanut · 2026-09-11
- KV cache gets QAT too: why this model beats others at fp4 KV cache — stochasticchasm · 2026-09-11
- Commentary: Anthropic loads shift to Google plus AWS slice, OpenAI doubles down on Azure — ericwdolan · 2026-09-11
- Nvidia claims Vera Rubin delivers 50X throughput per MW and 35X lower token cost vs Blackwell Ultra — Beth_Kindig · 2026-09-11
- Epoch AI: GPT long-context latency scales quadratically, matching price jumps — Jsevillamol · 2026-09-11
- RTX 3090 mini-bench: ninfer cuts TTFT from 3.4s to 29ms, prompt processing ~76x faster — milkipedia · 2026-09-11