llamaperf
Sep 11, 2026
Throughput
2.0 t/s gen
Quant
Q3 (GGUF)
System RAM
512 GB
VRAM reported
48 GB

Summary

User reports about 2 t/s running DeepSeek-R1-0528 Q3 GGUF on 2x RTX 3090 with 48 GB VRAM and 512 GB DDR5 system RAM. No engine is named. The user asks for upgrade advice to reach 15+ t/s with a very large model, and asks about Threadripper, EPYC and Xeon platforms.