My Q4 model said True where BF16 said False, so I diffed them layer by layer
This story is from 2026-10-17. It is preserved in the archive; the latest stories are on the live feed.
Qwen3-0.6B in BF16 reads this: def is_prime ( n ): if n 2 : return and puts 97.9% on False . The Q4_K_M quant of the same model puts 79.1% on True . That's one token out of 1,282 I scored. Across the whole text, Q4_K_M changes the top token at 11.6% of positions, its mean KL from BF16 is 0.067, and…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-17 16:53 · DEV Community — Machine Learning
My Q4 model said True where BF16 said False, so I diffed them layer by layer