科技前沿原文全文
Anemll (@anemll) on X
Hacker News 原文发布：2026年10月18日 01:58 · 北京时间
Post
Post
Anemll on X: "Confirmed 24K context on iPhone with both K/V on int8. Delta net stays FP16. Decoding also peaks at 70 tok/s with easy to predict context. Apple Neural Engine on A20 is fast 🚀"
Confirmed 24K context on iPhone with both K/V on int8. Delta net stays FP16. Decoding also peaks at 70 tok/s with easy to predict context. Apple Neural Engine on A20 is fast 🚀
00:00
Qwen 3.8- 27B on iPhone 18 Apple Neural Engine. Added draft model , dflash-2 at ~ 2.8 bpw ( mixed 2-4 vector quantization with small drop in acceptance rate) Base is @PrismML Bonsai-2, 1.585 bpw requantized to 1.5 bpw ( VQ 6 bits per 4 weights) Decoding speed is 15-60 tps.
00:00
信息从哪里来
- Hacker News 原始来源