14 points | by stared a day ago ago
3 comments
Yeah, there is latest and greatest trend: 0-bit quant. Absolutely outstanding performance, can produce as many tokens per second as you terminal may sustain with zero load on unified memory / GPU. Real winner!
Hmm, makes the 2 bit quants actually seem pretty reasonable…
[flagged]
Yeah, there is latest and greatest trend: 0-bit quant. Absolutely outstanding performance, can produce as many tokens per second as you terminal may sustain with zero load on unified memory / GPU. Real winner!
Hmm, makes the 2 bit quants actually seem pretty reasonable…
[flagged]