Vilda

Let's enjoy the ride; you only live once.

[Vilda @vildavedo]

@CodeWithAmann I'm still wondering how to load 7 GB models on an iPhone, which is a basic thing in the S26 Ultra.

[Vilda @vildavedo]

@ornith_ Can we get 4b model? 9b ran locally at S25U, but it's hard core. 😂

[Vilda @vildavedo]

@ornith_ I am running Ornith-1.0-35B-GGUF:BF16 on an RX 6900 XT + Threadripper 3970X with 128 GB RAM.

It's very impressive. From my testing in Zed editor over Ollama-Vulkan, it's between GPT-5.3 xHigh and 5.4 High.

I'm ready to donating to dev process, no limits, local data, that's it.

[Vilda @vildavedo]

@Ok_Dot7494 Yeah, models are far better than GPT-4o. Why do you still want that model?

[Vilda @vildavedo]

@M47429M @lucidwing17 1. Please use English.
2. Given the existence of numerous models possessing capabilities akin to GPT-4o, what specific challenges or issues are being encountered?

[Vilda @vildavedo]

@SapientFoo1 @lucidwing17 Yes! It would be appreciated if you could respect OpenAI's decision. They own their model and have no obligation to operate inefficient, underperforming models on costly modern infrastructure, especially since you have the liberty to utilize models such as GPT-4o on your device.

[Vilda @vildavedo]

@Anthony39218878 @JoeWilliams010 @sama What kind of power? Gemma 4e4b can be run on a smartphone and it's equally powerful. Gemma 31B can be run on a single GPU at home and it's far more capable than 4o.

Bro, stop living under the rock. 😉

[Vilda @vildavedo]

@_HislilLustFoxy @OpenAI Just host any open-source model on your device. Even S25U can run far more powerful model than 4o, lol.

[Vilda @vildavedo]

@stark4833 @OpenAI xDDDDDDDDDD

[Vilda @vildavedo]

@JoeWilliams010 @sama Totally stupid model, which even can't generate proper script or even correct sentences.

Just host local model, all local models are far better than 4o, lol.

[Vilda @vildavedo]

@mistralvibe Ok, where is better model? We need smth mathcing Claude, Gemini and GPT...

[Vilda @vildavedo]

@itsolelehmann Mistral is just piece of shit...

[Vilda @vildavedo]

@MrImranPk Them

[Vilda @vildavedo]

@TaraBull Them

[Vilda @vildavedo]

@mrrFail @sama The 4o model is stupid; it has been surpassed by other models, even small, locally capable ones.

[Vilda @vildavedo]

@mrrFail @sama You are so ohio, most people have no idea what it is and gpt4o wasn't able to generate basic stupid script.

[Vilda @vildavedo]

@UniverseIce S25U with the latest OneUI 8.5, and I have only 2 mods.

[Vilda @vildavedo]

@sflorimm Depends, if I pick science oriented topics or research. Gemini is just ahead of time.

[Vilda @vildavedo]

@QuantumDom Poland