DeepSeek V4 Flash 284B (13B active)
on Unknown GPU
Summary
User reports about 3-4 t/s generation on a Xeon w7-3465 CPU with DDR5-4800 RDIMM in a 4-channel configuration.
The model is DeepSeek-V4-Flash-0731 with 13B active experts and MXFP4 weights.
The user notes the speed is far below theoretical memory bandwidth and discusses thread settings and memory bandwidth issues.