# Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s (1.5 bpw) > Source: > Published: 2026-10-17 18:10:21+00:00 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 🚀 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. 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 🚀 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.