Qwen 3.8 Tested on 128GB Mac: Smarter but Memory-Hungry
Tests on a 128GB MacBook Pro M5 Max via MTPLX show Qwen 3.8 Flash Next is smarter and faster than the 27B model but needs about 80GB of RAM, while throughput drops sharply as context windows grow.
2026-09-01 ~ 2026-09-01 · 2 related posts
- Qwen 2.5 72B local test shows 50% throughput drop at long context — julianharris · 2026-09-01
- Qwen 3.8 Flash Next tested on a 128GB Mac: smarter and faster than 27B, needs ~80GB RAM — julianharris · 2026-09-01