DeepSeek V4 Flash 284B (13B active)
on M5 Pro 24GB · Mference
Summary
User reports DeepSeek-V4-Flash 284B-A13B at 4.8 tok/s on a 24 GB M5 Pro with about 5.3 GB of memory in use.
Setup is Mference, an open-source engine. The user also runs Gemma 4 26B-A4B and Qwen 3.6 35B-A3B.