TEST #869 RESULTS
05/14/2025 - 4:51 PM
ACCELERATOR
MODEL
43.2
tokens/s
generation
1.40
sec
time to first token
814
tokens/s
prompt
293
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 30B A3B - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.8.0-59-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #61~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 17:03:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1012
tokens/s
43.8
tokens/s
1.03
sec
pp4096+tg256
962
tokens/s
40.8
tokens/s
4.28
sec
pp2048+tg256
1038
tokens/s
42.3
tokens/s
1.99
sec
pp2048+tg768
1019
tokens/s
41.9
tokens/s
2.03
sec
pp1024+tg1024
975
tokens/s
42.3
tokens/s
1.07
sec
pp1280+tg3072
941
tokens/s
41.5
tokens/s
1.39
sec
pp384+tg1152
921
tokens/s
44.5
tokens/s
439
ms
pp64+tg1024
343
tokens/s
45.3
tokens/s
208
ms
pp16+tg1536
113
tokens/s
46.4
tokens/s
162
ms