LeaseWeb amd-epyc-9334-genoa-dual DeepSeek-R1-0528-Qwen3-8B FP16 TTFT s
8100.0 ms
Fields
id
benchmarks/lw-epyc9334-dual-deepseek8b-fp16-ttftMetric
ttft_ms
Value
8,100
Unit
ms
Model
DeepSeek-R1-0528-Qwen3-8B
Methodology
LeaseWeb benchmark (HPE ProLiant DL385 Gen11, dual EPYC 9334 32C Zen4, 64GB DDR5; L4 reference single GPU). llama-bench + OpenLLM/llmperf. 512-token prompt, 128 generated, 24 CPU threads for LLM runs. TTFT s.
Measured by
third_party
Reproducible
yes
Thermal state
unknown
notes
Dual-socket EPYC 9334 (2x32C) unless L4. LLM at 24 threads.
Notes
Dual-socket EPYC 9334 (2x32C) unless L4. LLM at 24 threads.