←back to thread

Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally

(ollama.com)
182 points BUFU | 3 comments | 06 Nov 24 21:10 UTC | HN request time: 0.917s | source
Show context
Patrick_Devine ◴[06 Nov 24 22:36 UTC] No.42070613[source]▶
This was a pretty heavy lift for us to get out which was why it took a while. In addition to writing new image processing routines, a vision encoder, and doing cross attention, we also ended up re-architecting the way the models get run by the scheduler. We'll have a technical blog post soon about all the stuff that ended up changing.
replies(4): >>42070644 #>>42071917 #>>42072723 #>>42076774 #
1. csomar ◴[07 Nov 24 02:34 UTC] No.42072723[source]▶
Any info of when we will get the 11B and 90B models?
replies(1): >>42076770 #
2. jjice ◴[07 Nov 24 14:09 UTC] No.42076770[source]▶
Not sure if I'm misunderstanding, but they're live: https://ollama.com/library/llama3.2-vision

Ran the 11B yesterday and it worked great.

replies(1): >>42083795 #
3. csomar ◴[08 Nov 24 03:22 UTC] No.42083795[source]▶
These are vision optimized, though? Or that doesn't make them perform less for coding tasks?