Qwen3.8-27B runs on the iPhone 18 Neural Engine at 15-70 tok/s (1.5 bpw)
anemll · hn · 2026-10-18
ANEMLL demonstrates Qwen3.8-27B running fully on-device with 1.5-bit quantization, hitting 15-70 tokens/s on the iPhone 18 Neural Engine — no cloud required.
More from Infra
- SGLang Summit sponsors grow from 11 to 36 in one week; Lip-Bu Tan, Lilian Weng to speak — BanghuaZ · 2026-10-18
- Yacine jokes his datacenter KPI is gigawatt-hours: get paged if not burning enough power — yacineMTB · 2026-10-18
- OpenAI reportedly handled ~15T tokens daily in April, likely higher now — JoshPurtell · 2026-10-18
- 1.68x inference speedup drops, directly accelerating GRPO post-training — yacineMTB · 2026-10-18
- OpenRouter is only a fraction of the total addressable market, poster argues — sloppenheimer · 2026-10-18
- Developer builds change alerts for LLM prices and retirements across Bedrock, Azure and Vertex — jsandhu0780 · 2026-10-18