# Hassan trains Tev1 0.8B, a tiny Jev-like classifier

The model runs entirely on his Mac through Ollama and, by his account, classifies tasks in about 50 ms end to end. Weights and benchmarks are not available yet; Hassan says both will be released very soon.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:46:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/f928e90041114d2d852b1273.html

Content language: en
Localization state: sameLanguage

Source: Hassan · Published 9/24/2026, 13:44:53

Hassan says he has trained Tev1 0.8B, a tiny classifier he describes as Jev-like. On his Mac, it runs fully locally through Ollama and classifies tasks.

He puts end-to-end latency for that local run at about 50 ms. The weights and benchmarks are not available yet, and Hassan says he will release them very soon.

Tags: Tev1, Ollama, Local inference, Classifiers

[View original post](https://x.com/nutlope/status/2103183092428984413)