Qwen3-Omni Technical Report · HackerPapers discussions

Qwen3-Omni Technical Report — mentioned by red2awn

Wed, 10 Dec 2025 20:19:56 GMT

They had a Flash variant released alongside the original open weight release. It is also mentioned in Section 5 of the paper: https://arxiv.org/pdf/2509.17765 For the evals it's probably just trained on a lot of the benchmark adjacent datasets compared to the 235B model. Similar thing happened on other model today: https://x.com/NousResearch/status/1998536543565127968 (a 30B model trained specifically to do well in maths get near SOTA scores)

Paper and discussion history. A mention is not an endorsement.

Qwen3-Omni Technical Report — mentioned by red2awn

Wed, 10 Dec 2025 20:15:34 GMT

It is an in-house closed weight model for their own chat platform, mentioned in Section 5 of the original paper: https://arxiv.org/pdf/2509.17765 I've seen it in their online materials too but can't seem to find it now.

Paper and discussion history. A mention is not an endorsement.

Qwen3-Omni Technical Report — HN submission

Fri, 26 Sep 2025 18:20:43 GMT

Qwen3-Omni: first multimodal model with SoTA text, image, audio, and video perf

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Qwen3-Omni Technical Report — mentioned by ltdemey

Thu, 25 Sep 2025 14:23:40 GMT

In Section 5 of their [technical report](https://arxiv.org/pdf/2509.17765v1) they mention them "... A comprehensive evaluation was performed on a suite of models, including Qwen3-Omni-30B-A3B- Instruct, Qwen3-Omni-30B-A3B-Thinking, and two in-house developed variants, designated Qwen3- Omni-Flash-Instruct and Qwen3-Omni-Flash-Thinking. These “Flash” models were designed to improve both computational efficiency and performance efficacy, integrating new functionalities, notably the support for various dialects. ..."

Paper and discussion history. A mention is not an endorsement.

Qwen3-Omni Technical Report — mentioned by daemonologist

Tue, 23 Sep 2025 22:32:25 GMT

Their A3B Omni paper mentions that the Omni at that size outperformed the (unreleased I guess) VL. Edit: I see now that there is no Omni-235B-A22B; disregard the following. ~~Which is interesting - I'd have expected the larger model to have more weights to "waste" on additional modalities and thus for the opposite to be true (or for the VL to outperform in both cases, or for both to benefit from knowledge transfer).~~ Relevant comparison is on page 15: https://arxiv.org/abs/2509.17765

Paper and discussion history. A mention is not an endorsement.