Qwen 3.8-27B takes 5 minutes to think on M5 MacBook Pro
talkaboutdesign · x · 2026-08-15
A user tested the Qwen3.8-27B model on an M5 MacBook Pro with 64GB of RAM. When asked a simple question about actors in programming, the model "thought" for 5 minutes without outputting a result, forcing the user to stop the process due to excessive friction. The user expressed anticipation for the day when such models can run fast on local hardware.
More from Infra
- 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
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16