Evidence brief
UnslothAI says 2-bit NVIDIA Nemotron 3.5 Lightning used only 22GB VRAM to run tool calling continuously for 10 minutes. During the process, the model cited more than 80 websites, executed code, and searched 10 real locations; it can be run and trained via Unsloth Desktop.
UnslothAI says 2-bit NVIDIA Nemotron 3.5 Lightning used only 22GB VRAM to run tool calling continuously for 10 minutes. During the process, the model cited more than 80 websites, executed code, and searched 10 real locations; it can be run and trained via Unsloth Desktop.
This brief preserves the original source so the summary and editorial context can be checked independently.
Source attributionX · @UnslothAI
Open the original sourceRelationships are derived from shared topics, entities, categories, tags, and community context; every result remains independently source-linked.
The post says NVIDIA researchers built SparDA, adding a Forecast projection beyond Q, K, and V to use the previous layer to predict the KV blocks needed by the next layer; this variant makes decoding 1.7x faster and improves long-reasoning accuracy by 6.5 points.
Original sourceLTX launched the LTX-2.5 model with native ComfyUI integration; on a setup with 2 NVIDIA GB200s, generating a 10-second 720P video takes 6.8 seconds, and LTX-2.5 Fast is priced at $0.09 per second.
Original sourceThe repost shows NVIDIAAI introducing NVIDIA Nemotron 3.5 Lightning, an open 30B MoE model with 3B active parameters, designed for always-on agents scenarios.
Original sourceThe Sakana AI team launched a major Sakana Chat update. The service requires no login and is free to use, powered by Fugu and the updated Namazu Japanese LLM, with full code execution support.
Original sourceOpenRouter releases a tool-calling guide explaining how to switch between Claude, GPT, and open-weight models with the same code, covering tool definition, requests, and result-return loops.
Original source