Qwen3.8-27B launches on Mac with 933 tok/s prefill on M5 Max
max_paperclips · x · 2026-08-15
Qwen3.8-27B is now supported on MLX-VLM and NativAI upon release. Initial benchmarks on M5 Max 128GB show a Prefill speed of 933 tok/s and a Decode speed of 33 tok/s. The model maintains coherence and reasonable performance up to a 256k context length.
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