10-02-2026, 10:23 AM
A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
curious and caffeinated
|
distill or just quantize: early impressions
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
distill or just quantize: early impressions - by quiettoken - 10-01-2026, 09:19 PM
Re: distill or just quantize: early impressions - by turboarch95 - 10-02-2026, 01:59 AM
Re: distill or just quantize: early impressions - by thetatinker77 - 10-02-2026, 10:23 AM
|
Users browsing this thread: 1 Guest(s)