TEST #57 RESULTS
03/28/2025 - 8:47 PM
ACCELERATOR
MODEL
52.0
tokens/s
generation
692
ms
time to first token
1883
tokens/s
prompt
521
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7543 32-Core Processor (znver3)
RAM
503.7GB
OS
Linux
Kernel Release
5.4.0-155-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #172-Ubuntu SMP Fri Jul 7 16:10:02 UTC 2023
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2205
tokens/s
53.7
tokens/s
483
ms
pp4096+tg256
1799
tokens/s
47.0
tokens/s
2.30
sec
pp2048+tg256
2038
tokens/s
51.2
tokens/s
1.03
sec
pp2048+tg768
2052
tokens/s
50.7
tokens/s
1.02
sec
pp1024+tg1024
2218
tokens/s
52.6
tokens/s
481
ms
pp1280+tg3072
2145
tokens/s
49.6
tokens/s
616
ms
pp384+tg1152
2254
tokens/s
53.7
tokens/s
201
ms
pp64+tg1024
1717
tokens/s
54.8
tokens/s
55
ms
pp16+tg1536
516
tokens/s
54.3
tokens/s
48
ms