News for hackers. Stuff that matters.

A comment on April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini. Parent comment

Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by DiabloD3 on Friday April 03, 2026 @08:49AM (#47626098)
I don't think it does, but llama.cpp does, and can load models off HuggingFace directly (so, not limited to ollama's unofficial model mirror like ollama is).

There is no reason to ever use ollama.

[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by ffsm8 on Friday April 03, 2026 @09:04AM (#47626213)
> I don't think it does, but llama.cpp does

I just checked their docs and can't see anything like it.

Did you mistake the command to just download and load the model?

[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by u8080 on Friday April 03, 2026 @09:47AM (#47626618)
-hf ModelName:Q4_K_M
[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by ffsm8 on Friday April 03, 2026 @10:05AM (#47626797)
Did you mistake the command to just download and load the model too?

Actually that shouldn't be a question, you clearly did.

Hint: it also opens Claude code configured to use that model

[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by DiabloD3 on Friday April 03, 2026 @08:38PM (#47634270)
As a sibling comment answered you, it is `-hf`.

And yes, it downloads the model, caches it, and then serves future loads of that model out of the cache if the file hasn't changed in the hf repo.

[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by ffsm8 on Friday April 03, 2026 @08:55PM (#47634397)
So I'm summary: no, it does not have an equivalent command either.
[ Parent | on HN ]
Re:April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac... by beanjuiceII on Friday April 03, 2026 @09:13AM (#47626311)
sure there's a reason...it works fine thats the reason
[ Parent | on HN ]