Open models by OpenAI • Hacker News Board

Re: Open models by OpenAI

#11

Post by Workaccount2 » Tue, Aug 05, 2025, 5:08 PM UTC

Wow, today is a crazy AI release day:

- OAI open source

- Opus 4.1

- Genie 3

- ElevenLabs Music

Re: Open models by OpenAI

#12

Post by hnuser123456 » Tue, Aug 05, 2025, 5:09 PM UTC

DSingularity wrote: post #6

Ha. Secure funding and proceed to immediately make a decision that would likely conflict viscerally with investors.

Maybe someone got tired of waiting paid them to release something actually open

Re: Open models by OpenAI

#13

Post by deviation » Tue, Aug 05, 2025, 5:10 PM UTC

So this confirms a best-in-class model release within the next few days?

From a strategic perspective, I can't think of any reason they'd release this unless they were about to announce something which totally eclipses it?

Re: Open models by OpenAI

#14

Post by artembugara » Tue, Aug 05, 2025, 5:10 PM UTC

Disclamer: probably dumb questions

so, the 20b model.

Can someone explain to me what I would need to do in terms of resources (GPU, I assume) if I want to run 20 concurrent processes, assuming I need 1k tokens/second throughput (on each, so 20 x 1k)

Also, is this model better/comparable for information extraction compared to gpt-4.1-nano, and would it be cheaper to host myself 20b?

Re: Open models by OpenAI

#15

Post by thimabi » Tue, Aug 05, 2025, 5:10 PM UTC

coreyh14444 wrote: post #4

thimabi wrote: post #3

Open weight models from OpenAI with performance comparable to that of o3 and o4-mini in benchmarks… well, I certainly wasn’t expecting that. What’s the catch?

Because GPT-5 comes out later this week?

It could be, but there’s so much hype surrounding the GPT-5 release that I’m not sure whether their internal models will live up to it.

For GPT-5 to dwarf these just-released models in importance, it would have to be a huge step forward, and I’m still doubting about OpenAI’s capabilities and infrastructure to handle demand at the moment.

Re: Open models by OpenAI

#16

Post by hubraumhugo » Tue, Aug 05, 2025, 5:11 PM UTC

Meta's goal with Llama was to target OpenAI with a "scorched earth" approach by releasing powerful open models to disrupt the competitive landscape. Looks like OpenAI is now using the same playbook.

Re: Open models by OpenAI

#17

Post by k2xl » Tue, Aug 05, 2025, 5:12 PM UTC

Is there any details about hardware requirements for a sensible tokens per second for each size of these models?

Re: Open models by OpenAI

#18

Post by orphea » Tue, Aug 05, 2025, 5:12 PM UTC

Workaccount2 wrote: post #11

Wow, today is a crazy AI release day: - OAI open source - Opus 4.1 - Genie 3 - ElevenLabs Music

  OAI open source

Yeah. This certainly was not on my bingo card.

Re: Open models by OpenAI

#19

Post by mythz » Tue, Aug 05, 2025, 5:14 PM UTC

artembugara wrote: post #14

Disclamer: probably dumb questions so, the 20b model. Can someone explain to me what I would need to do in terms of resources (GPU, I assume) if I want to run 20 concurrent processes, assuming I need 1k tokens/second throughput (on each, so 20 x 1k) Also, is this model better/comparable for information extraction compared to gpt-4.1-nano, and would it be cheaper to host myself 20b?

gpt-oss:20b is ~14GB on disk [1] so fits nicely within a 16GB VRAM card.

[1] https://ollama.com/library/gpt-oss

Re: Open models by OpenAI

#20

Post by minimaxir » Tue, Aug 05, 2025, 5:14 PM UTC

I'm disappointed that the smallest model size is 21B parameters, which strongly restricts how it can be run on personal hardware. Most competitors have released a 3B/7B model for that purpose.

For self-hosting, it's smart that they targeted a 16GB VRAM config for it since that's the size of the most cost-effective server GPUs, but I suspect "native MXFP4 quantization" has quality caveats.