Argonne MI250 llama.cpp Mixtral-8x7B b1
17.2 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi250-llamacpp-mixtral-8x7b-fp16-b1-128io-tpsMetric
tps_aggregate
Value
17.2
Unit
tok/s aggregate (batch*(in+out)/lat)
Model
mistralai/Mixtral-8x7B-v0.1
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136, All_results.csv). llama.cpp, FP16/BF16, 128in/128out, AGGREGATE over batch. 1 tile bs1 lat 14.89s. CSV 'AMD MI250 GPU' = Polaris MI250.
Measured by
third_party
Reproducible
yes