Phi4 Available on Ollama

Re:Phi4 Available on Ollama by mark_l_watson on Sunday January 12, 2025 @11:50AM (#42674851)

I am blown away: a year ago I bought a M2 32G Mac to run local models. It seems like what I can run locally now just one year later is 10x more useful for NLP, data wrangling, RAG, experimenting with agents, etc.

BTW, a few days ago I published a book on using Ollama. Here is a link to red it online https://leanpub.com/ollama/read

[ Parent | on HN ]

Re:Phi4 Available on Ollama by hn8726 on Sunday January 12, 2025 @02:23PM (#42676088)

Which models do you recommend for that amount of memory?

[ Parent | on HN ]

Re:Phi4 Available on Ollama by rpastuszak on Sunday January 12, 2025 @03:06PM (#42676425)

I asked the same question a few days back and I'm keeping the responses here: https://bsky.app/profile/potato.horse/post/3lejngewfmc2n

[ Parent | on HN ]

Re:Phi4 Available on Ollama by mark_l_watson on Tuesday January 14, 2025 @11:04AM (#42698935)

For reasoning: qwq:latest (19G file)

For coding: qwen2.5-coder:14b (9G file)

Misc. experiments, runs fast: llama3.2:latest )2 G file)

[ Parent | on HN ]