| ▲ | stymaar an hour ago | |
Anyone calling Qwen3.6-35B-A3B-Q4_K_XL “rubish” has no idea what they are talking about. | ||
| ▲ | embedding-shape an hour ago | parent | next [-] | |
I'd agree that the quality degrades a lot between Q8 and Q4, borderline unusable as they start to fail with tool calling syntax even. Personally I'd say Q8 is as low as you want to go. | ||
| ▲ | c0rruptbytes an hour ago | parent | prev | next [-] | |
q4 isn't rubbish, but it's a compromise for a good value, q6 is essentially a no-compromise quantization and it's what i recommend for MoEs in my experience for agentic workflows | ||
| ▲ | greenavocado an hour ago | parent | prev [-] | |
He's probably calling me out for this comment https://news.ycombinator.com/item?id=48557579 | ||