TEST #3384 RESULTS
04/25/2026 - 6:19 PM
ACCELERATOR
MODEL
33.2
tokens/s
generation
1.22
sec
time to first token
1044
tokens/s
prompt
305
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7251 8-Core Processor
RAM
220.3GB
OS
Linux
Kernel Release
6.17.0-22-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #22~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Mar 26 15:25:54 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1279
tokens/s
35.0
tokens/s
830
ms
pp4096+tg256
1031
tokens/s
30.6
tokens/s
4.01
sec
pp2048+tg256
1168
tokens/s
33.1
tokens/s
1.78
sec
pp2048+tg768
1156
tokens/s
32.6
tokens/s
1.80
sec
pp1024+tg1024
1218
tokens/s
33.5
tokens/s
870
ms
pp1280+tg3072
1145
tokens/s
31.4
tokens/s
1.15
sec
pp384+tg1152
1236
tokens/s
34.1
tokens/s
339
ms
pp64+tg1024
887
tokens/s
34.6
tokens/s
120
ms
pp16+tg1536
274
tokens/s
34.2
tokens/s
86
ms