Model Releases
Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 vs the same model writing JSON: ⏳ ~1/3 less time for a yes/no on …
Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 vs the same model writing JSON: ⏳ ~1/3 less time for a yes/no on a full photo 🤑 up to ~85% less GPU cost with many Qs per imag
Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 vs the same model writing JSON: ⏳ ~1/3 less time for a yes/no on a full photo 🤑 up to ~85% less GPU cost with many Qs per image 🎯 same accuracy on fresh photos: level with the best hosted models on pick-one (0.933 vs 0.937), ~2 pts behind Gemini on yes/no pip install glance-vlm http://github.com/yoheinakajima/glance
Related
Source: Yohei Nakajima (X) | 2026-09-21