I think this is old news, but this model does better than llama 4 maverick on coding.
by torginus
5 subcomments
I wonder why are we getting these drops during the weekend. Is the AI race truly that heated?
by
0 subcomment
by xpe
1 subcomments
The about page doesn’t shed light on the composition of the core team nor their sources of incomes or funding. Am I overlooking something?
> We are a group of people with diverse talents and interests.
by Alifatisk
0 subcomment
I’ve tried QVQ before, one issue I always stumbled upon is that it entered an endless loop of reasoning. It felt wrong letting it run for too long, I didn’t want to over consume Alibabas gpus.
I’ll try QVQ-Max when I get home. It’s kinda fascinating how these models can interpret an image and actually understand what is in it and reason around it. So cool.
by AbuAssar
1 subcomments
Naming things is truly hard even for the smartest people.
by ttul
0 subcomment
Just going off the blog post, this seems like a multimodal LLM that uses thinking tokens. That’s pretty cool. Is this the first of its kind?
by unixhero
0 subcomment
So how do I run it locally?
by gatienboquet
1 subcomments
Isn't "thinking" in image mode basically what chatgpt 4o image generation do ?
Hacker News