Homi, open decision model for audio, near Flash on MMSU and 50x cheaper
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Homi is an open-weights audio decision model built on frozen Qwen3-Omni-30B with a 17M-parameter LoRA and a decision head that outputs calibrated probabilities over options rather than generated text.