Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
tongyi-agent.github.io
Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
1–10 of 156 posts
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#2This is over a month old, they released the weights a long time ago.
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#3Isn't OpenIA "Deep research" (not "DeepResearch") a methodology/tooling thing, and you'll get different responses depending on what specific model you use with it? As far as the UI allows you to, you could use Deep research with GPT-5, GPT-4o, o3 and so on, and that'll have an impact on the responses. Skimming the paper and searching for some simple terms makes it seem like they never expand on what exact models they've used, just that they've used a specific feature from ChatGPT?
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#4This is over a month old, they released the weights a long time ago.
And for those not so tightly in the loop: how does it compare?
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#5Sunday morning, and I find myself wondering how the engineering tinkerer is supposed to best self-host these models? I'd love to load this up on the old 2080ti with 128gb of vram and play, even slowly. I'm curious what the current recommendation on that path looks like.
Constraints are the fun part here. I know this isn't the 8x Blackwell Lamborghini, that's the point. :)
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#6It's a Qwen 3 MoE fine tune...
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#7Sunday morning, and I find myself wondering how the engineering tinkerer is supposed to best self-host these models? I'd love to load this up on the old 2080ti with 128gb of vram and play, even slowly. I'm curious what the current recommendation on that path looks like. Constraints are the fun part here. I know this isn't the 8x Blackwell Lamborghini, that's the point. :)
llama.cpp gives you the most control to tune it for your machine.
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#8It makes me wonder if we'll see an explosion of purpose trained LLMs because we hit diminishing returns on invest with pre training or if it takes a couple of months to fold these advantages back into the frontier models.
Given the size of frontier models I would assume that they can incorporate many specializations and the most lasting thing here is the training environment.
But there is probably already some tradeoff, as GPT 3.5 was awesome at chess and current models don't seem trained extensively on chess anymore.
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#9This whole series of work is quite cool. The use of `word-break: break-word;` makes this really hard to read though.
Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch
#10I hope the translation for this is actually "Agree" Deep research.
Just a dig at "You are absolutely right!" sycophancy.