MLX Fast speeds up Qwen 3.8 27B by 153% on Apple Silicon
alexcovo_eth · x · 2026-08-17
Developer shares progress on MLX Fast optimizing the Qwen 3.8 27B model: under 16 hours, performance improved by 153% over baseline and 2.5x faster than out-of-the-box MTP decode. The tool targets Apple Silicon architecture, challenging the belief that Macs are slow at dense models via speculative decoding.
Related event: MLX Optimization Challenge Speeds Up Qwen 27B on Apple Silicon by Over 150%(4 posts)→
More from Infra
- Three CoreWeave co-founders have sold $3.3B in shares since IPO amid credit worries — SumitGup · 2026-10-16
- Cherry pi on a Raspberry Pi: the tiny-model rumor developers are watching — sull · 2026-10-16
- CoreWeave's debt costs falling: DDTL spreads tightened from S+9.62% to S+2.25% — BenBajarin · 2026-10-16
- SoftBank lines up US IPOs for SB Energy and AI robotics spinoff Roze, valuations top $50B — nordicinst · 2026-10-16
- TRL reproduces Modal's mixed-precision async RL: plain GRPO collapses, SC+MIS holds 0.72 — QGallouedec · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16