Running large language models (LLMs) on your local machine has become increasingly popular, offering privacy, offline access, and customization. Ollama is a ...
ollama is getting less and less open, and (IMO) should not be used. If that doesn’t concern you, you should be using LM Studio anyway.
The model sizes they mention are mostly for old models no-one should be using. The only exception is a 70B MoE (Hunyuan), but I think ollama doesn’t even support that?
The quantization methods they mention are (comparatively) primitive and low performance, not cutting edge.
It mentions q8_0 twice, nonsensically… Um, it makes me think this article is AI slop?
I’m glad opensuse is promoting local LLM usage, but please… not ollama, and be more specific.
And don’t use ollama to write it without checking :/
It also sets context length to 2k by default iirc, which breaks a lot of tasks, and gives a general bad first impression to users who are likely using local models for the first time.
I hate to drone on about this again, but:
ollama is getting less and less open, and (IMO) should not be used. If that doesn’t concern you, you should be using LM Studio anyway.
The model sizes they mention are mostly for old models no-one should be using. The only exception is a 70B MoE (Hunyuan), but I think ollama doesn’t even support that?
The quantization methods they mention are (comparatively) primitive and low performance, not cutting edge.
It mentions q8_0 twice, nonsensically… Um, it makes me think this article is AI slop?
I’m glad opensuse is promoting local LLM usage, but please… not ollama, and be more specific.
And don’t use ollama to write it without checking :/
It also sets context length to 2k by default iirc, which breaks a lot of tasks, and gives a general bad first impression to users who are likely using local models for the first time.
Yes, and it’s hard to undo, and not obvious!