Palm-Infra open-sourced: Run 284B models on MacBook via SSD offloading

dr_cintas · x · 2026-08-26

Tencent's Palm-Infra framework enables running massive MoE models on Apple Silicon by streaming experts directly from SSD. Benchmarks show DeepSeek-V4-Flash (284B) decoding at 5.71 tps and a 122B model at 16.53 tps on an M5 Pro with 20GB memory, achieving capabilities previously impossible with llama.cpp.

Related event: Tencent Open-Sources Palm-Infra, Running 284B Models on a MacBook(2 posts)→

Original post →

More from Infra

Infra channel →