TEST #47 RESULTS
03/28/2025 - 7:03 PM
ACCELERATOR
MODEL
34.1
tokens/s
generation
1.20
sec
time to first token
1100
tokens/s
prompt
315
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7702 64-Core Processor (znver2)
RAM
503.5GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1271
tokens/s
35.2
tokens/s
834
ms
pp4096+tg256
1029
tokens/s
30.9
tokens/s
4.01
sec
pp2048+tg256
1174
tokens/s
33.7
tokens/s
1.77
sec
pp2048+tg768
1172
tokens/s
33.3
tokens/s
1.78
sec
pp1024+tg1024
1268
tokens/s
34.6
tokens/s
836
ms
pp1280+tg3072
1226
tokens/s
32.7
tokens/s
1.07
sec
pp384+tg1152
1339
tokens/s
35.4
tokens/s
314
ms
pp64+tg1024
1092
tokens/s
36.0
tokens/s
107
ms
pp16+tg1536
331
tokens/s
35.5
tokens/s
75
ms