Fully automated tracker discovers new Hugging Face models within a day and estimates max tok/s
helloiamleonie · x · 2026-09-03
Developer onusoz showcases an LLM-based, fully automated open-weight model tracker that has ingested 6 months of model discussion on X. It discovers and analyzes any new Hugging Face model within a day, estimates theoretical max tok/s on your hardware using the author's own formulation, and aggregates community sentiment. The author plans manual re-evaluation, and demos LFM 2.5 2.6b for in-browser embedded use cases.
More from coding & agent
- Open-source coding agent Pi hits 100,000 GitHub stars, v2 teased — gklambauer · 2026-09-03
- Codebase-specific agent harnesses may beat general-purpose ones, argues secemp9 — secemp9 · 2026-09-03
- Teknium runs Hermes Agent for 15 hours with recursive subagents, shedding 375,000 lines of code — Teknium · 2026-09-03
- Building a local Gemma planner-executor-critic agent pipeline for web research — HlddenDreck · 2026-09-03
- Dev builds Arcon: a local AI assistant on Qwen3-4B with memory, mood and tools — Feathered-Beast · 2026-09-03
- After DeepSeek Harness: why agent harnesses still lack any scientific evaluation — samrauh · 2026-09-03