Live data from Hacker News

Qwen2.5-VL-32B: Smarter and Lighter

qwenlm.github.io

231–240 of 303 posts

Re: Qwen2.5-VL-32B: Smarter and Lighter

#231
post #150

Earlier quoted context omitted.

One possibility. Certain countries will always be able to produce open models cheaper than others. USA and Europe probably won't be able. However, due to national security and wanting to promote their models overseas instead of letting their competitors promote theirs, the governments of USA and Europe will subsidize models which will lead their competitors to (further?) subsidies. There is a promotional aspect as we…

What's your take on why certain countries will have it cheaper and subsidies being at the forefront? An energy driven race to the bottom, is perhaps what you mean? I would suppose I have been seeing that China is ahead on their Renewables plan compared to the rest of the world, and they still have the lead on coal energy, so they'd likely be the winners on that front. But did you actually mean something else?

Energy is definitely a major factor but other factors too. Cheaper infrastructure (data centers), cheaper components including GPUs (once that is cracked) and cheaper data collection (web scraping, surveillance infrastructure, etc). Any novel idea that improves the architectures of models in the future will inadvertently get leaked quickly and then all these other factors come into play. Countries that cannot make models this cheap will subsidize models for national security reasons and promoting their country's interest reasons.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#232
post #18

Earlier quoted context omitted.

Since we are on HN here, I can highly recommend open-webui with some OpenAI-compatible provider. I'm running with Deep Infra for more than a year now and am very happy. New models are usually available within one or two days after release. Also have some friends who use the service almost daily.

I'm using open-webui at home with a couple of different models. gemma2-9b fits in VRAM on a NV 3060 card + performs nicely.

> performs nicely

Do you have rough indication of token/s ?

Re: Qwen2.5-VL-32B: Smarter and Lighter

#233
post #18

Earlier quoted context omitted.

it seems that this free version "may use your prompts and completions to train new models" https://openrouter.ai/deepseek/deepseek-chat-v3-0324:free do you think this needs attention?

Since we are on HN here, I can highly recommend open-webui with some OpenAI-compatible provider. I'm running with Deep Infra for more than a year now and am very happy. New models are usually available within one or two days after release. Also have some friends who use the service almost daily.

I've tried using it, but it's browser tab seems to peg one core to 100% after some time. Anyone else experienced it?

Re: Qwen2.5-VL-32B: Smarter and Lighter

#234
post #134

Earlier quoted context omitted.

That 1% discount feels a bit cheap to me - if it was a 25% or 50% discount I would be much more likely to sign up for it.

We don’t particularly want our customers’ data :)

You clearly want it a little if you give a discount for it?

Re: Qwen2.5-VL-32B: Smarter and Lighter

#235

Earlier quoted context omitted.

I tried R1 through Kagi and it’s similarly censored. Even the distill of llama running on Groq is censored.

Kagi may be using the official DeepSeek API and not hosting the model itself. There is work being done to make it completely uncensored: https://github.com/huggingface/open-r1 https://ollama.com/huihui_ai/deepseek-r1-abliterated I was mistaken though, it is more than just a system prompt causing the censorship.

Kagi uses R1 through Fireworks.ai, Together.ai and Groq.

https://help.kagi.com/kagi/ai/llms-privacy.html

Re: Qwen2.5-VL-32B: Smarter and Lighter

#236
post #110

This model is available for MLX now, in various different sizes. I ran https://huggingface.co/mlx-community/Qwen2.5-VL-32B-Instruct... using uv (so no need to install libraries first) and https://github.com/Blaizzy/mlx-vlm like this: uv run --with 'numpy That downloaded an ~18GB model and gave me a VERY impressive result, shown at the bottom here: https://simonwillison.net/2025/Mar/24/qwen25-vl-32b/

Does quantised MLX support vision though?

Is UV the best way to run it?

Re: Qwen2.5-VL-32B: Smarter and Lighter

#237

We were using Llama vision 3.2 a few months back and were very frustrated with it (both in term of speed and results quality). Some day we were looking for alternatives on Hugging Face and eventually stumbled upon Qwen. The difference in accuracy and speed absolutely blew our mind. We ask it to find something in an image and we get a response in like half a second with a 4090 and it's most of the time correct. What's…

Ever since I switched to Qwen as my go to, it's been a bliss. They have a model for many (if not all) cases. No more daily quota! And you get to use their massive context window (1M tokens).

Re: Qwen2.5-VL-32B: Smarter and Lighter

#238
post #166

Earlier quoted context omitted.

Oh, I have a question, maybe you know. Assuming the same model sizes in gigabytes, which one to choose: a higher-B lower-bit or a lower-B higher-bit? Is there a silver bullet? Like “yeah always take 4-bit 13B over 8-bit 7B”. Or are same-sized models basically equal in this regard?

I would say 9 times out of 10, you will get better results from a Q4 model that’s a size class larger than a smaller model at Q8. But it’s best not to go below Q4.

My understanding is that models are currently undertrained and not very "dense", so Q4 doesn't hurt very much now but it may in future denser models.

Re: Qwen2.5-VL-32B: Smarter and Lighter

#239

We were using Llama vision 3.2 a few months back and were very frustrated with it (both in term of speed and results quality). Some day we were looking for alternatives on Hugging Face and eventually stumbled upon Qwen. The difference in accuracy and speed absolutely blew our mind. We ask it to find something in an image and we get a response in like half a second with a 4090 and it's most of the time correct. What's…

what do you use to serve it, ollama or llama.cpp or similar?

Re: Qwen2.5-VL-32B: Smarter and Lighter

#240

Any security risks running these Chinese LLMs on my local computer?

Just based on the stage of the game I'd say it's not likely, but the possibilities are there:

https://news.ycombinator.com/item?id=43121383

It would have to be from unsupervised tool usage or accepting backdoored code, not traditional remote execution from merely inferencing the weights.

Post reply on HN