{"ok":true,"trend":{"id":785734,"platform":"mastodon","region":"global","key":"originally published on my blog. enabling mtp on this rtx 3090 raised generation throughput from... # ai # llm # program","title":"Originally published on my blog. Enabling MTP on this RTX 3090 raised generation throughput from... # ai # llm # program","url":"https://www.urbanmind.net/display/f7dd981d-54dbaf58-7bbb66c0ced7a116","first_seen":"2026-10-02T22:30:29.375863Z","last_seen":"2026-10-03T01:15:47.239736Z","last_rank":7,"peak_rank":1,"last_volume":5,"peak_volume":5,"seen_count":3,"score":0.993125,"category_hint":"software","section":"technology","category":"software","summary":"A developer reports enabling multi-token prediction (MTP) on an RTX 3090 graphics card raised local LLM generation throughput, while questioning whether the speedup affects coding quality. The write-up, originally published on a personal blog, has drawn attention from AI and open-source software communities interested in getting more performance from consumer GPUs for running large language models locally.","why":"Hobbyists running local LLMs are keen to learn performance tricks for consumer hardware like the RTX 3090.","tone":"neutral","entities":["RTX 3090","NVIDIA","multi-token prediction"],"summarized_at":"2026-10-02T22:31:19.827262Z","meta":{"tag":"programming","via":"scan","kind":"status","lang":"en","instance":"mastodon.social","tag_uses":100},"nw":null,"promo":null,"kind":null,"importance":null,"hidden":false,"hide_reason":null,"judged_at":null,"title_en":"Multi-Token Prediction Boosts RTX 3090 LLM Speed","section_name":"Technology","category_name":"Software","timeline":[{"captured_at":"2026-10-02T22:30:29.375863Z","rank":1,"volume":5},{"captured_at":"2026-10-02T22:30:29.375863Z","rank":7,"volume":5},{"captured_at":"2026-10-02T23:53:07.010141Z","rank":7,"volume":5},{"captured_at":"2026-10-03T01:15:47.239736Z","rank":7,"volume":5}],"posts":[{"platform":"mastodon","url":"https://www.urbanmind.net/display/f7dd981d-54dbaf58-7bbb66c0ced7a116","author":"hackaday@www.urbanmind.net","title":null,"snippet":"Originally published on my blog. Enabling MTP on this RTX 3090 raised generation throughput from... # ai # llm # programming # opensource # software # coding # development # engineering # inclusive # community MTP on an RTX 3090: Faster Tokens, but What About Coding Quality?","posted_at":"2026-10-02T21:22:39Z","likes":5}],"elsewhere":[],"window":"7d"}}