alt Hacker NewsQwen3.5: Towards Native Multimodal Agents
Comments
Does anyone else have trouble loading from the qwen blogs? I always get their placeholders for loading and nothing ever comes in. I don’t know if this is ad blocker related or what… (I’ve even disabled it but it still won’t load)
For those interested, made some MXFP4 GGUFs at https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF and a guide to run them: https://unsloth.ai/docs/models/qwen3.5
Pelican is OK, not a good bicycle: https://gist.github.com/simonw/67c754bbc0bc609a6caedee16fef8...
Would love to see a Qwen 3.5 release in the range of 80-110B which would be perfect for 128GB devices. While Qwen3-Next is 80b, it unfortunately doesn't have a vision encoder.
I just started creating my own benchmarks (very simple questions for humans but tricky for AI, like how many r's in strawberry kind of questions, still WIP).
Qwen3.5 is doing ok on my limited tests: https://aibenchy.com
Last Chinese new year we would not have predicted a Sonnet 4.5 level model that runs local and fast on a 2026 M5 Max MacBook Pro, but it's now a real possibility.
Going by the pace, I am more bullish that the capabilities of opus 4.6 or latest gpt will be available under 24GB Mac
Sad to not see smaller distills of this model being released alongside the flaggship. That has historically been why i liked qwen releases. (Lots of diffrent sizes to pick from from day one)
Great benchmarks, qwen is a highly capable open model, especially their visual series, so this is great.
Interesting rabbit hole for me - its AI report mentions Fennec (Sonnet 5) releasing Feb 4 -- I was like "No, I don't think so", then I did a lot of googling and learned that this is a common misperception amongst AI-driven news tools. Looks like there was a leak, rumors, a planned(?) launch date, and .. it all adds up to a confident launch summary.
What's interesting about this is I'd missed all the rumors, so we had a sort of useful hallucination. Notable.
Does anyone know what kind of RL environments they are talking about? They mention they used 15k environments. I can think of a couple hundred maybe that make sense to me, but what is filling that large number?
Already on open router, prices seem quite nice.
at this point it seems every new model scores within a few points of each other on SWE-bench. the actual differentiator is how well it handles multi-step tool use without losing the plot halfway through and how well it works with an existing stack
From the HuggingFace model card [1] they state:
> "In particular, Qwen3.5-Plus is the hosted version corresponding to Qwen3.5-397B-A17B with more production features, e.g., 1M context length by default, official built-in tools, and adaptive tool use."
Anyone knows more about this? The OSS version seems to have has 262144 context len, I guess for the 1M they'll ask u to use yarn?
Is it just me or are the 'open source' models increasingly impractical to run on anything other than massive cloud infra at which point you may as well go with the frontier models from Google, Anthropic, OpenAI etc.?
Let's see what Grok 4.20 looks like, not open-weight, but so far one of the high-end models at real good rates.
Wow, the Qwen team is pushing out content (models + research + blogpost) at an incredible rate! Looks like omni-modals is their focus? The benchmark look intriguing but I can’t stop thinking of the hn comments about Qwen being known for benchmaxing.
Anyone else getting an automatically downloaded PDF 'ai report' when clicking on this link? It's damn annoying!
Yes, but does it answer questions about Tiananmen Square?
Does anyone know the SWE bench scores?
Is it just me or is the page barely readable? Lots of text is light grey on white background. I might have "dark" mode on on Chrome + MacOS.
You'll be pleased to know that it chooses "drive the car to the wash" on today's latest embarrassing LLM question.