TEST #95 RESULTS
03/28/2025 - 9:29 PM
ACCELERATOR
MODEL
24.9
tokens/s
generation
488
ms
time to first token
2867
tokens/s
prompt
527
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9354 32-Core Processor (znver4)
RAM
755.6GB
OS
Linux
Kernel Release
6.5.0-45-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jul 15 16:40:02 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4002
tokens/s
26.6
tokens/s
294
ms
pp4096+tg256
2412
tokens/s
21.4
tokens/s
1.75
sec
pp2048+tg256
3214
tokens/s
24.0
tokens/s
679
ms
pp2048+tg768
3223
tokens/s
23.6
tokens/s
677
ms
pp1024+tg1024
4007
tokens/s
25.1
tokens/s
294
ms
pp1280+tg3072
3626
tokens/s
23.0
tokens/s
393
ms
pp384+tg1152
3873
tokens/s
26.3
tokens/s
135
ms
pp64+tg1024
1120
tokens/s
27.5
tokens/s
93
ms
pp16+tg1536
328
tokens/s
26.9
tokens/s
83
ms