Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3-VL

qwen.ai

Post reply on HN
Print view View original

81–90 of 166 posts

Re: Qwen3-VL

#81

Post by Alifatisk »

unixhero wrote: post #47
richardlblair wrote: post #23

As I mentioned yesterday - I recently needed to process hundreds of low quality images of invoices (for a construction project). I had a script that had used pil/opencv, pytesseract, and open ai as a fallback. It still has a staggering number of failures. Today I tried a handful of the really poor quality invoices and Qwen spat out all the information I needed without an issue. What's crazier is it gave me the boundi…

So where did you load up Qwen and how did you supply the pdf or photo files? I don't know how to use these models, but want to learn

You can use their models here chat.qwenlm.ai, its their official website

Re: Qwen3-VL

#82

Post by Alifatisk »

Wow, the Qwen team doesn't stop and keep coming up with surprises. Not only did they release this but also the new Qwen3-Max model

Re: Qwen3-VL

#84

Post by spaceman_2020 »

deepdarkforest wrote: post #8

The Chinese are doing what they have been doing to the manufacturing industry as well. Take the core technology and just optimize, optimize, optimize for 10x the cost/efficiency. As simple as that. Super impressive. These models might be bechmaxxed but as another comment said, i see so many that it might as well be the most impressive benchmaxxing today, if not just a genuinely SOTA open source model. They even relea…

Interestingly, I've found that models like Kimi K2 spit out more organic, natural-sounding text than American models

Fails on the benchmarks compared to other SOTA models but the real-world experience is different

Re: Qwen3-VL

#85

Post by WithinReason »

Jackson__ wrote: post #72
Workaccount2 wrote: post #54

Sadly it still fails the "extra limb" test. I have a few images of animals with an extra limb photoshopped onto them. A dog with an leg coming out of it's stomach, or a cat with two front right legs. Like every other model I have tested, it insists that the animals have their anatomically correct amount of limbs. Even pointing out there is a leg coming from the dogs stomach, it will push back and insist I am confused…

It fails on any edge case, like all other VLMs. The last time a vision model succeeded at reading analog clocks, a notoriously difficult task, it was revealed they trained on nearly 1 million artificial clock images[0] to make it work. In a similar vein, I have encountered no model that could read for example a D20 correctly.[1] It could probably identify extra limbs in your pictures if you too made a million example…

I can't tell which number is up either since it's on a white background, am I an LLM?

Re: Qwen3-VL

#86

Post by wiz21c »

richardlblair wrote: post #23

As I mentioned yesterday - I recently needed to process hundreds of low quality images of invoices (for a construction project). I had a script that had used pil/opencv, pytesseract, and open ai as a fallback. It still has a staggering number of failures. Today I tried a handful of the really poor quality invoices and Qwen spat out all the information I needed without an issue. What's crazier is it gave me the boundi…

I like to test these models on reading the contents of 80's Apple ][ games screenshots. These are very low resolution, very dense. All (free to use) models struggle on that task...

Re: Qwen3-VL

#87

Post by isoprophlex »

Extremely impressive, but can one really run these >200B param models on prem in any cost effective way? Even if you get your hands on cards with 80GB ram, you still need to tie them together in a low-latency high-BW manner.

It seems to me that small/medium sized players would still need a third party to get inference going on these frontier-quality models, and we're not in a fully self-owned self-hosted place yet. I'd love to be proven wrong though.

Re: Qwen3-VL

#88

Post by te0006 »

buyucu wrote: post #69
whitehexagon wrote: post #68

Imagine the demand for a 128GB/256GB/512GB unified memory stuffed hardware linux box shipping with Qwen models already up and running. Although I´m agAInst steps towards AGI, it feels safer to have these things running locally and disconnected from each other, than some giant GW cloud agentic data centers connected to everyone and everything.

I bought an GMKtec evo 2 that is a 128 GB unified memory system. Strong recommend.

Interesting - do you need to take any special measures to get OSS genAI models to work on this architecture? Can you use inference engines like Ollama and vLLM off-the-shelf (as Docker containers) there, with just the Radeon 8060S GPU? What token rates do you achieve?

(edit: corrected mistake w.r.t. the system's GPU)

Re: Qwen3-VL

#89

Post by Borealid »

isoprophlex wrote: post #87

Extremely impressive, but can one really run these >200B param models on prem in any cost effective way? Even if you get your hands on cards with 80GB ram, you still need to tie them together in a low-latency high-BW manner. It seems to me that small/medium sized players would still need a third party to get inference going on these frontier-quality models, and we're not in a fully self-owned self-hosted place yet. I…

A Framework Desktop exposes 96GB of RAM for inference and costs a few thou USD.

Re: Qwen3-VL

#90

Post by jwr »

jychang wrote: post #21
deepdarkforest wrote: post #8

The Chinese are doing what they have been doing to the manufacturing industry as well. Take the core technology and just optimize, optimize, optimize for 10x the cost/efficiency. As simple as that. Super impressive. These models might be bechmaxxed but as another comment said, i see so many that it might as well be the most impressive benchmaxxing today, if not just a genuinely SOTA open source model. They even relea…

They still suck at explaining which model they serve is which, though. They also released today Qwen3-VL Plus [1] today alongside Qwen3-VL 235B [2] and they don't tell us which one is better. Note that Qwen3-VL-Plus is a very different model compared to Qwen-VL-Plus. Also, qwen-plus-2025-09-11 [3] vs qwen3-235b-a22b-instruct-2507 [4]. What's the difference? Which one is better? Who knows. You know it's bad when OpenA…

> They still suck at explaining which model they serve is which, though.

"they" in this sentence probably applies to all "AI" companies.

Even the naming/versioning of OpenAI models is ridiculous, and then you can never find out which is actually better for your needs. Every AI company writes several paragraphs of fluffy text with lots of hand waving, saying how this model is better for complex tasks while this other one is better for difficult tasks.

Post reply on HN