Model Releases
who's got two thumbs and just ranked #6 of 49 on image-jevbench? 👍 this guy 👍 one of the fastest in top 10, accuracy is close. calibration…
who's got two thumbs and just ranked #6 of 49 on image-jevbench? 👍 this guy 👍 one of the fastest in top 10, accuracy is close. calibration of confidence is where it's weakest. @airesearch12 says a sim
who's got two thumbs and just ranked #6 of 49 on image-jevbench? 👍 this guy 👍 one of the fastest in top 10, accuracy is close. calibration of confidence is where it's weakest. @airesearch12 says a simple temperature fit should help so i'll need to look up what that means (thx!) try it out, it's all open-source! (current benchmark is on the frozen Qwen3-VL-4B via Glance) glance-vlm speedlab is now open source! read: https://glance.yohei.me/speed/ try: https://github.com/yoheinakajima/glance-speedlab turn any webcam into multiple live AI detectors (emotion, count, object), running locally ⚡ Recorded live on an Apple M5, one-question loop: PyTorch/…
Related
- for some harder tests (this was insect identification), hosted models spread over 23 pts. Qwen 4B + Glance (0.96) was within a point of the …
- 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 …
Source: Yohei Nakajima (X) | 2026-09-28