alt Hacker NewsIn initial testing on Ryzen 395 / Strix Halo it's about 22 tokens/s generation and the output quality is impressive. Better and faster than 3.8 27B, and enough better to justify moving away from 3.6 35B even though 35B is still faster. The Unsloth weights don't come with vision support but you can add that back yourself. llama.cpp recipe in case anyone else wants to save some time on setup: https://pastebin.com/fcqsbDTv
Replies
data-ottawa • today at 7:05 PM
We should still expect significant performance improvements.
I believe Unsloth’s branch (and ggml’s) don’t support MTP or the ngram embedding yet.
➕ show 1 reply
> Better... than 3.8 27B
How can a "6b active per token" MoE be better than a just released 27b in the same family? Possible maybe, but quite interesting and requiring some explanation.
Edit: ok, on second thought, probably because the small "experts" are really rich in specialized training compared to the dense model. Still raising questions about the details, e.g. the reasoning abilities (or all meta-skills) of a "6b per token" network compared to the dense capabilities...