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

Open models by OpenAI

openai.com

Post reply on HN
Print view View original

381–390 of 909 posts

Re: Open models by OpenAI

#381

Post by datadrivenangel »

cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

Now to embrace jevon's paradox and expand usage until we're back to draining lakes so that your agentic refrigerator can simulate sentience.

Re: Open models by OpenAI

#382

Post by herval »

datadrivenangel wrote: post #381
cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

Now to embrace jevon's paradox and expand usage until we're back to draining lakes so that your agentic refrigerator can simulate sentience.

In the future, your Samsung fridge will also need your AI girlfriend

Re: Open models by OpenAI

#383

Post by black3r »

cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

can you please give an estimate how much slower/faster is it on your macbook compared to comparable models running in the cloud?

Re: Open models by OpenAI

#384

Post by hrpnk »

simonw wrote: post #338

Just posted my initial impressions, took a couple of hours to write them up because there's a lot in this release! https://simonwillison.net/2025/Aug/5/gpt-oss/ TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. Will be interesting to see if independent benchmarks resolve in that direction as well. The 20B model runs on my Mac laptop using less than 15GB…

I tried to generate a streamlit dashboard with MACD, RSI, MA(200). 1:0 for qwen3 here.

qwen3-coder-30b 4-bit mlx took on the task w/o any hiccups with a fully working dashboard, graphs, and recent data fetched from yfinance.

gpt-oss-20b mxfp4's code had a missing datatime import and when fixed delivered a dashboard without any data and with starting date of Aug 2020. Having adjusted the date, the update methods did not work and displayed error messages.

Re: Open models by OpenAI

#385

Post by Shank »

Invictus0 wrote: post #339
Shank wrote: post #271

Earlier quoted context omitted.

That doesn’t sound good. It sounds like OpenAI will route my request to the cheapest model to them and the most expensive for me, with the minimum viable results.

Sounds just like what a human would do. Or any business for that matter.

That may be true but I thought the promise was moving in the direction of AGI/ASI/whatever and that models would become more capable over time.

Re: Open models by OpenAI

#386

Post by parhamn »

cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

I just tested 120B from the Groq API on agentic stuff (multi-step function calling, similar to claude code) and it's not that good. Agentic fine-tuning seems key, hopefully someone drops one soon.

Re: Open models by OpenAI

#387

Post by hrpnk »

coltonv wrote: post #374
simonw wrote: post #338

Just posted my initial impressions, took a couple of hours to write them up because there's a lot in this release! https://simonwillison.net/2025/Aug/5/gpt-oss/ TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. Will be interesting to see if independent benchmarks resolve in that direction as well. The 20B model runs on my Mac laptop using less than 15GB…

What did you set the context window to? That's been my main issue with models on my macbook, you have to set the context window so short that they are way less useful than the hosted models. Is there something I'm misisng there?

With LM Studio you can configure context window freely. Max is 131072 for gpt-oss-20b.

Re: Open models by OpenAI

#388

Post by hrpnk »

GodelNumbering wrote: post #372
simonw wrote: post #338

Just posted my initial impressions, took a couple of hours to write them up because there's a lot in this release! https://simonwillison.net/2025/Aug/5/gpt-oss/ TLDR: I think OpenAI may have taken the medal for best available open weight model back from the Chinese AI labs. Will be interesting to see if independent benchmarks resolve in that direction as well. The 20B model runs on my Mac laptop using less than 15GB…

> The 20B model runs on my Mac laptop using less than 15GB of RAM. I was about to try the same. What TPS are you getting and on which processor? Thanks!

gpt-oss-20b: 9 threads, 131072 context window, 4 experts - 35-37 tok/s on M2 Max via LM Studio.

Re: Open models by OpenAI

#389

Post by mathiaspoint »

cco wrote: post #357

The lede is being missed imo. gpt-oss:20b is a top ten model (on MMLU (right behind Gemini-2.5-Pro) and I just ran it locally on my Macbook Air M3 from last year. I've been experimenting with a lot of local models, both on my laptop and on my phone (Pixel 9 Pro), and I figured we'd be here in a year or two. But no, we're here today. A basically frontier model, running for the cost of electricity (free with a rounding…

It's really training not inference that drains the lakes.

Re: Open models by OpenAI

#390

Post by AtlasBarfed »

narrator wrote: post #159
4b6442477b1280b wrote: post #99

Earlier quoted context omitted.

in that era, OpenAI and Anthropic were still deluding themselves into thinking they would be the "stewards" of generative AI, and the last US administration was very keen on regoolating everything under the sun, so "safety" was just an angle for regulatory capture. God bless China.

Yeah, China is e/acc. Nice cheap solar panels too. Thanks China. The problem is their ominous policies like not allowing almost any immigration, and their domestic Han Supremacist propaganda, and all that make it look a bit like this might be Han Supremacy e/acc. Is it better than wester/decel? Hard to say, but at least the western/decel people are now starting to talk about building power plants, at least for datace…

Oh poor oppressed marc andreesen. Someone save him!
Post reply on HN