←back to thread

Qwen3-Omni-Flash-2025-12-01：a next-generation native multimodal large model

(qwen.ai)
314 points pretext | 1 comments | 10 Dec 25 16:13 UTC | HN request time: 0.803s | source
Show context
banjoe ◴[10 Dec 25 17:20 UTC] No.46220493[source]▶
Wow, crushing 2.5 Flash on every benchmark is huge. Time to move all of my LLM workloads to a local GPU rig.
replies(3): >>46220593 #>>46223561 #>>46229791 #
1. skrunch ◴[11 Dec 25 10:41 UTC] No.46229791[source]▶
Except the image benchmarks are compared against 2.0, which seems suspicious that they would casually drop to an older model for those.