35 comments

[ 3.5 ms ] story [ 59.6 ms ] thread
I wonder if with that music analysis mode, you can also make your own synths
Does Qwen3-Omni support real-time conversation like GPT-4o? Looking at their documentation it doesn't seem like it does.

Are there any open weight models that do? Not talking about speech to text -> LLM -> text to speech btw I mean a real voice <-> language model.

edit:

It does support real-time conversation! Has anybody here gotten that to work on local hardware? I'm particularly curious if anybody has run it with a non-nvidia setup.

None of inference frameworks (vLLM/SGLang) supports the full model, let alone non-nvidia.
That's exciting. I doubt there are any polished voice chat local apps yet that you can easily plug this into (I doubt the user experience is "there" yet). Even stuff like Silly Tavern is near unusable, lots of work to be done on the local front. Local voice models are what's going to enable that whole Minority Report workflow soon enough (especially if commands and intent are determined at the local level, and the meat of the prompt is handled by a larger remote model).

This is part of programming that I think is the new field. There will be tons of work for those that can build the new workflows which will need to be primarily natural language driven.

From what I can tell, their official chat site doesn't have a native audio -> audio model yet. I like to test this through homophones (e.g. record and record) and asking it to change its pitch or produce sounds.
Does anyone else find that there's hard to pin down reason of life-lessness in the speech of these voice models?

Especially in the fruit pricing portion of the video for this model. Sounds completely normal but I can immediately tell it is ai. Maybe it's intonation or the overly stable rate of speech?

I'm not convinced its end-to-end multimodal - in that case, you'll have a speech synthesis section and this will be some of the result. You could test by having it sing or do some accents, or have it talk back to you in an accent you give it.
GPT4o in the charts is crazy.
Wow, crushing 2.5 Flash on every benchmark is huge. Time to move all of my LLM workloads to a local GPU rig.
Why would you use an Omni model for text only workload... There is Qwen3-30B-A3B.
Except the image benchmarks are compared against 2.0, which seems suspicious that they would casually drop to an older model for those.
This is a 30B parameter MoE with 3B active parameters and is the successor to their previous 7B omni model. [1]

You can expect this model to have similar performance to the non-omni version. [2]

There aren't many open-weights omni models so I consider this a big deal. I would use this model to replace the keyboard and monitor in an application while doing the heavy lifting with other tech behind the scenes. There is also a reasoning version, which might be a bit amusing in an interactive voice chat if it pronounces the thinking tokens while working through to a final answer.

1. https://huggingface.co/Qwen/Qwen2.5-Omni-7B

2. https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct

I can't find the weights for this new version anywhere. I checked modelscope and huggingface. It looks like they may have extended the context window to 200K+ tokens but I can't find the actual weights.
> There is also a reasoning version, which might be a bit amusing in an interactive voice chat if it pronounces the thinking tokens while working through to a final answer.

last i checked (months ago) claude used to do this

> This is a 30B parameter MoE with 3B active parameters

Where are you finding that info? Not saying you're wrong; just saying that I didn't see that specified anywhere in the linked page, or on their HF.

I was wrong. I confused this with their open model. Looking at it more closely, it is likely an omni version of Qwen3-235B-A22B. I wonder why they benchmarked it against Qwen2.5-Omni-7B instead of Qwen3-Omni-30B-A3B.

I wish I could delete the comment.

This is a stack of models:

- 650M Audio Encoder

- 540M Vision Encoder

- 30B-A3B LLM

- 3B-A0.3B Audio LLM

- 80M Transformer/200M ConvNet audio token to waveform

This is a closed source weight update to their Qwen3-Omni model. They had a previous open weight release Qwen/Qwen3-Omni-30B-A3B-Instruct and a closed version Qwen3-Omni-Flash.

You basically can't use this model right now since none of the open source inference framework have the model fully implemented. It works on transformers but it's extremely slow.

I dont think the Flash model discussed in the article is 30B

Their benchmark table shows it beating Qwen3-235B-A22B

Does "Flash" in the name of a Qwen model indicate a model-as-a-service and not open weights?

Haha, you could hear how it’s mind thinks, maybe by putting a lot of reverb on the thinking tokens or some other effect…
(comment deleted)
Is this a new proprietary model?
The main issue I'm facing with realtime responses (speech output) is how to separate non-diegetic outputs (e.g thinking, structured outputs) from outputs meant to be heard by the end user.

I'm curious how anyone has solved this

Is there a way to run these Omni models on a Macbook quantized via GGUF or MLX? I know I can run it in LMStudio or Llama.cpp but they don't have streaming microphone support or streaming webcam support.

Qwen usually provides example code in Python that requires Cuda and a non-quantized model. I wonder if there is by now a good open source project to support this use case?

Wow, just 32B? This could almost run on a good device with 64 GB RAM. Once it gets to Ollama I'll have to see just what I can get out of this.
Interesting - when I asked the omni model at qwen.com what version it was, I got a testy "I don't have a version" and then was told my chat was blocked for inappropriate content. A second try asking for knowledge cutoff got me the more equivocal "2024, but I know stuff after that date, too".

No idea how to check if this is actually deployed on qwen.com right now.

I truly enjoy how the naming conventions seem to follow how I did homework assignments back in the day: finalpaper-1-dec2nd, finalpaper-2-dec4th, etc etc.
Having lots of success with Gemini Flash Live 2.5. I am hoping 3.0 to come out soon. Benchmarks here claim better results that Gemini Live but have to test it. In past I've always been disappointed with Qwen Omni models in my English-first case...
Qwen seem to be deliberately confusing about if they are releasing models open weight or not. I think largely not any more and you can go on quite a wild goose chase looking for different things that are implied they are released but are actually only available via API.