Hermes Agent on my RTX 5090 with a local model: about 93 tok/s, averaged over an hour of…
This is a vibe coding post classified by AGK Intelligence as Agent infra & costs (a showcase), kept by the Vibe Coding Radar because it carries real work, not commentary.
Hermes Agent on my RTX 5090 with a local model: about 93 tok/s, averaged over an hour of real agent work. Qwen3.8-27B 6-bit file, the model's MTP draft switched on in llama.cpp, a q8_0 cache and 128k context. - about 93 tok/s generated over one hour-long Hermes Agent goal run (297,736 tokens) - 93 to 97 tok/s across five runs of the same kind - new prompt tokens read at about 2,100 to 2,200 tok/s - 128k context loads at 27.0 of the card's 31.8 GiB, 192k at 29.8, the model's full 262k does not fit on a 32 GB card, run this file at 128k with the MTP draft and a q8_0 cache. 192k fits too, but
Posted by witcheer (22.9k followers) 7 days ago · 105 likes · 8.1k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs.
More vibe coding work like this
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- Build an agent on @onkeiki to answer your customers while you sleep. — @orchid_hq
- how do you stop 20+ agents from colliding on the same client work? — @webjuice_ie
- Brilliant paper on optimizing agent environments. — @dair_ai
- Docker is one box. The coding agent can run in others, and switching is one line 🧰 — @marcelotryle
- Holy f*cking sh*t... everyone upgrades Claude and nobody builds the harness — @gippp69
- 1/9 — @TollyLabs
- As AI coding agents get more capable, knowing what they're doing becomes just as… — @EntelligenceAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:07 UTC. Full method.