Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
appvoid 
posted an update 19 days ago
Post
902
granite-4.0-350m, rwkv7-g1d-0.4b and LFM2-350M are currently the best sub 0.5b models currently for fewshot, simple language tasks

no one is saying this:

if you need the absolute speed + small size + quality, granite 350m is the current king

if you need raw power though slow, rwkv 0.4b has you covered, if you need something in between choose lfm2 350m

rwkv 0.4b is actually fast :) please use https://github.com/BlinkDL/Albatross

·

I guess the reason is slow is because llama.cpp is not optimized...

In this post