Pinned
I've uploaded Q4, Q8 and BF16 MTP draft models in their own repo
It should work natively with yesterday's llama.cpp merge
Espen JD
4,346 posts
Espen JD
@Snixtp
Cyber Network Engineer | Codex enthusiast | Local AI | RTX Pro 6000 enjoyer
Joined June 2020
- Replying to @indykaila and @realmadridCome on Indy, don’t destroy your reputation like this please
- Replying to @greggmunikwaTrent leaving was necessary for it to be a super team tbh
- Replying to @TheImmortalKopI love robbo for the corner taken quickly, but this fella is good, best crosser we've had.
