Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s (1.5 bpw)

Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s (1.5 bpw)

Article URL: https://twitter.com/anemll/status/2111517143087067309 Comments URL: https://news.ycombinator.com/item?id=50133500 Points: 12 # Comments: 2

Comment