Show HN: 8-bit Qwen3.8-27B decodes 1.7x faster than BF16, slower at 16K context
By gltanaka · 2026-08-19 · 1 points · 0 comments
https://github.com/promptdriven/pdd/tree/main/research/omlx-qwen38-quantization
By gltanaka · 1 points · 0 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews