TEST #1324 RESULTS
08/07/2025 - 6:11 AM
ACCELERATOR
MODEL
27.3
tokens/s
generation
2.59
sec
time to first token
516
tokens/s
prompt
176
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi3 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
578
tokens/s
31.2
tokens/s
1.81
sec
pp4096+tg256
475
tokens/s
17.4
tokens/s
8.68
sec
pp2048+tg256
534
tokens/s
24.4
tokens/s
3.87
sec
pp2048+tg768
534
tokens/s
23.1
tokens/s
3.88
sec
pp1024+tg1024
570
tokens/s
28.0
tokens/s
1.83
sec
pp1280+tg3072
556
tokens/s
21.4
tokens/s
2.34
sec
pp384+tg1152
589
tokens/s
31.8
tokens/s
679
ms
pp64+tg1024
526
tokens/s
35.3
tokens/s
146
ms
pp16+tg1536
283
tokens/s
33.2
tokens/s
80
ms