Lao Guo's Learning Space
Oct 27, 2026 · Artificial Intelligence
How Slotstream Runs a 105GB MoE Model on a 16GB Mac at 20 tok/s
Slotstream streams the 105GB Qwen3.8-Flash-Next MoE model from SSD on Apple Silicon Macs with as little as 16GB RAM, achieving 20–23 tok/s on a 48GB M5 Pro, though prefill latency and limited features remain trade-offs.
Apple SiliconLLM inferenceMoE
0 likes · 9 min read
