Simon P. Couch @simonpcouch.com · Dec 10

A new release of chores is now on #rstats CRAN! There are now some LLMs tiny enough to run on a laptop that are capable of powering chores helpers. Here's a real-time demo with a model running on my Macbook. Read more: www.simonpcouch.com/blog/2025-12...

26 likes 3 replies

?

Replies

Sharon Machlis · Dec 12

For ollama + Windows, I'm finding `ollama pull qwen3:4b-instruct` works better than `ollama pull qwen3:4b` overall. The 'regular' qwen3:4b seems VERY chatty (and slow) in ollama. ollama.com/library/qwen...

Sharon Machlis · Dec 10

You should be able to set the ollama default context window to a larger size? Context length - Ollama share.google/o8PMy6FBonGj...

McEnkidu · Dec 10

Did you manage to get speculative decoding in lm studio to work with the Qwen models?