TEST #93 RESULTS
03/28/2025 - 9:26 PM
ACCELERATOR
MODEL
24.7
tokens/s
generation
513
ms
time to first token
2713
tokens/s
prompt
508
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
6.8.0-50-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #51~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 21 12:03:03 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3745
tokens/s
25.9
tokens/s
314
ms
pp4096+tg256
2314
tokens/s
21.2
tokens/s
1.82
sec
pp2048+tg256
3053
tokens/s
23.9
tokens/s
713
ms
pp2048+tg768
3045
tokens/s
23.2
tokens/s
714
ms
pp1024+tg1024
3753
tokens/s
24.8
tokens/s
314
ms
pp1280+tg3072
3367
tokens/s
22.8
tokens/s
420
ms
pp384+tg1152
3680
tokens/s
26.2
tokens/s
142
ms
pp64+tg1024
1131
tokens/s
27.5
tokens/s
92
ms
pp16+tg1536
329
tokens/s
26.9
tokens/s
83
ms