Ollama: All Aboard Open Models • Hacker News Board

Re: Ollama: All Aboard Open Models

#11

Post by rvz » Sun, Jul 19, 2026, 3:14 PM UTC

> The local LLM ecosystem doesn’t need Ollama. It needs llama.cpp. The rest is packaging, and better packaging already exists.

Then put those LLMs to work and build an open source alternative to everything that Ollama is doing.

After all, open source is a pricing weapon to race everything to $0.

Re: Ollama: All Aboard Open Models

#12

Post by ekianjo » Sun, Jul 19, 2026, 3:20 PM UTC

dont use Ollama. llamacpp is better in every way.

Re: Ollama: All Aboard Open Models

#13

Post by wazoox » Sun, Jul 19, 2026, 3:35 PM UTC

Annoyingly many useful tools like the "Page Assist" browser extension or "Murmure" are plug-and-play only with Ollama...

Re: Ollama: All Aboard Open Models

#14

Post by lioeters » Sun, Jul 19, 2026, 3:53 PM UTC

> The personal computer moment for AI

Georgi Gerganov, the author of llama.cpp, is the real hero here.

https://llama.app/

Re: Ollama: All Aboard Open Models

#15

Post by joshdavham » Sun, Jul 19, 2026, 4:02 PM UTC

Cool to learn that the founders also had a hand in developing Docker Desktop in the past!

Re: Ollama: All Aboard Open Models

#16

Post by JSR_FDED » Sun, Jul 19, 2026, 4:03 PM UTC

The VCs listed in the article aren’t the dumbest ones around. Why on earth would they invest in a shell around the actual technology?

Were they so enraptured with the “docker for LLMs” line?

Re: Ollama: All Aboard Open Models

#17

Post by fragmede » Sun, Jul 19, 2026, 4:10 PM UTC

vivzkestrel wrote: post #6

- stop using ollama - https://sleepingrobots.com/dreams/stop-using-ollama/

If that's what I'd have to do to get $88 million, I don't want $88 million.

Re: Ollama: All Aboard Open Models

#18

Post by twsted » Sun, Jul 19, 2026, 4:27 PM UTC

Another chance to tip their hat to llama.cpp, missed. I really don't get it.

Re: Ollama: All Aboard Open Models

#19

Post by verdverm » Sun, Jul 19, 2026, 4:30 PM UTC

vivzkestrel wrote: post #6

- stop using ollama - https://sleepingrobots.com/dreams/stop-using-ollama/

I've been very happy with vLLM as an alternative on the serving side, and OpenCode Go on the subscription side

Re: Ollama: All Aboard Open Models

#20

Post by zishha1b0njq » Sun, Jul 19, 2026, 4:40 PM UTC

vivzkestrel wrote: post #6

- stop using ollama - https://sleepingrobots.com/dreams/stop-using-ollama/

This post is empty of any relevant content.

I wish HN would stop sharing drama-seeking posts, especially by anonymous authors, attacking the hard work of people.

Are ollama's authors perfect? No, they are just humans. But many people find their work valuable and we should support Open Source.

I can assure you that you won't like the world where nobody release Open Source projects anymore because of the constant negativity.