| ▲ | Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses(quesma.com) | |
| 14 points by stared a day ago | 3 comments | ||
| ▲ | Gerard22Aug 20 hours ago | parent | next [-] | |
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! | ||
| ▲ | kamranjon a day ago | parent | prev | next [-] | |
Hmm, makes the 2 bit quants actually seem pretty reasonable… | ||
| ▲ | freemindcore 10 hours ago | parent | prev [-] | |
[flagged] | ||