Qwen 3.8 27B runs 214.6% faster on Apple Silicon
StefanoGogioso · x · 2026-08-18
The author cites data showing that the Qwen 3.8 27B model now runs 214.6% faster on Apple Silicon. Based on this performance boost, the author argues that there is little doubt Apple will be the uncontested leader of local AI hardware. The data comes from an open leaderboard.
Related event: Qwen 3.8 27B Runs Nearly 3x Faster on Apple Silicon(2 posts)→
More from Infra
- Phison CEO calls CXMT memory scare a 'ghost story', warns of materials shortage — BenBajarin · 2026-10-16
- Ben Bajarin: The Future of Compute Is Fungible as Hyperscalers Design for Workload Flexibility — BenBajarin · 2026-10-16
- AirLLM runs frontier-size models layer-by-layer: 671B on 12GB VRAM — Aiden_Tech_Ai · 2026-10-16
- NVIDIA Launches cuPotential in CUDA-X to Bring AI Agents to Semiconductor Materials Simulation — tomaszbednarz · 2026-10-16
- Q4-quantized coder model on 8-core CPU builds interactive solar system demo in one shot — IntrepidMindExplorer · 2026-10-16
- TokenSpeed MLA 2 ships for Vera Rubin: up to 3.44× faster Kimi K3 decode — zhyncs42 · 2026-10-16