Open models by OpenAI • Hacker News Board

Re: Open models by OpenAI

#71

Post by jakozaur » Tue, Aug 05, 2025, 5:29 PM UTC

The coding seems to be one of the strongest use cases for LLMs. Though currently they are eating too many tokens to be profitable. So perhaps these local models could offload some tasks to local computers.

E.g. Hybrid architecture. Local model gathers more data, runs tests, does simple fixes, but frequently asks the stronger model to do the real job.

Local model gathers data using tools and sends more data to the stronger model.

It

Re: Open models by OpenAI

#72

Post by Imustaskforhelp » Tue, Aug 05, 2025, 5:29 PM UTC

Is this the same model (Horizon Beta) on openrouter or not? Because I still see Horizon beta available with its codename on openrouter

Re: Open models by OpenAI

#73

Post by Tostino » Tue, Aug 05, 2025, 5:30 PM UTC

artembugara wrote: post #29

mythz wrote: post #19

Earlier quoted context omitted.

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

thanks, this part is clear to me. but I need to understand 20 x 1k token throughput I assume it just might be too early to know the answer

I legitimately cannot think of any hardware that will get you to that throughput over that many streams with any of the hardware I know of (I don't work in the server space so there may be some new stuff I am unaware of).

Re: Open models by OpenAI

#74

Post by gnulinux » Tue, Aug 05, 2025, 5:30 PM UTC

sadiq wrote: post #41

Looks like Groq (at 1k+ tokens/second) and Fireworks are already live on openrouter: https://openrouter.ai/openai/gpt-oss-120b $0.15M in / $0.6-0.75M out edit: Now Cerebras too at 3,815 tps for $0.25M / $0.69M out.

Wow, that's significantly cheaper than o4-mini which seems to be on part with gpt-oss-120b. ($1.10/M input tokens, $4.40/M output tokens) Almost 10x the price.

LLMs are getting cheaper much faster than I anticipated. I'm curious if it's still the hype cycle and Groq/Fireworks/Cerebras are taking a loss here, or whether things are actually getting cheaper. At this we'll be able to run Qwen3-32B level models in phones/embedded soon.

Re: Open models by OpenAI

#75

Post by abidlabs » Tue, Aug 05, 2025, 5:30 PM UTC

Test it with a web UI: https://huggingface.co/spaces/abidlabs/openai-gpt-oss-120b-t...

Re: Open models by OpenAI

#76

Post by ArtTimeInvestor » Tue, Aug 05, 2025, 5:31 PM UTC

Why do companies release open source LLMs?

I would understand it, if there was some technology lock-in. But with LLMs, there is no such thing. One can switch out LLMs without any friction.

Re: Open models by OpenAI

#77

Post by Imustaskforhelp » Tue, Aug 05, 2025, 5:31 PM UTC

podnami wrote: post #48

sadiq wrote: post #41

Looks like Groq (at 1k+ tokens/second) and Fireworks are already live on openrouter: https://openrouter.ai/openai/gpt-oss-120b $0.15M in / $0.6-0.75M out edit: Now Cerebras too at 3,815 tps for $0.25M / $0.69M out.

Wow this was actually blazing fast. I prompted "how can the 45th and 47th presidents of america share the same parents?" On ChatGPT.com o3 thought for for 13 seconds, on OpenRouter GPT OSS 120B thought for 0.7 seconds - and they both had the correct answer.

Not gonna lie but I got sorta goosebumps

I am not kidding but such progress from a technological point of view is just fascinating!

Re: Open models by OpenAI

#78

Post by HanClinto » Tue, Aug 05, 2025, 5:31 PM UTC

Holy smokes, there's already llama.cpp support:

https://github.com/ggml-org/llama.cpp/pull/15091

Re: Open models by OpenAI

#79

Post by gnulinux » Tue, Aug 05, 2025, 5:31 PM UTC

sigmar wrote: post #64

sadiq wrote: post #41

Looks like Groq (at 1k+ tokens/second) and Fireworks are already live on openrouter: https://openrouter.ai/openai/gpt-oss-120b $0.15M in / $0.6-0.75M out edit: Now Cerebras too at 3,815 tps for $0.25M / $0.69M out.

Non-rhetorically, why would someone pay for o3 api now that I can get this open model from openai served for cheaper? Interesting dynamic... will they drop o3 pricing next week (which is 10-20x the cost[1])? [1] currently $3M in/ $8M out https://platform.openai.com/docs/pricing

Not even that, even if o3 being marginally better is important for your task (let's say) why would anyone use o4-mini? It seems almost 10x the price and same performance (maybe even less): https://openrouter.ai/openai/o4-mini

Re: Open models by OpenAI

#80

Post by winterrx » Tue, Aug 05, 2025, 5:31 PM UTC

deviation wrote: post #13

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?

GPT-5 coming Thursday.