Dory 1.0

Dory 1.0 is a newly tracked term on FastToolHub's radar. Source signal: X+HF+Web. Radar summary: NVIDIA Nemotron Labs Dory1.0-4B: open looped / latent-recurrent 4B LLM with 'elastic depth' — 8 input layers, shared 20-layer recurrent block, 8 output layers; n_recurrent_loops 1 (low latency) / 2 (default) / 4 (hard agentic tasks) on one checkpoint. HF repo created Oct 16, 145 likes / 2.5k downloads; NVFP4 & MXFP8 variants; write-ups Oct 19 (Laurence Moroney) and CN X post 'NVIDIA 正式开源循环语言模型 Dory 1.0' (Oct 20 23:49Z).

Dory 1.0 appears in the model / AI-system category: something teams would load, call, or fine-tune rather than a pure UI gadget. Mentions point at agent workflows — coding agents, computer-use, or tool-using loops. Open-source or public-repo signals show up in the excerpt, so inspection and self-hosting may be possible. Infrastructure / hardware angles (clusters, accelerators, factories) are part of the story. Do not invent parameters, prices, or benchmarks beyond what the excerpt already states.

Start from the primary link: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16. For models: verify context length, license, and hardware needs from official docs; run a small smoke test before production. For agent/product tools: try a narrow workflow first, keep secrets out of prompts, and log failures for later replay. Numbers and claims in this page only repeat the radar excerpt — double-check upstream before publishing.