TEST #1336 RESULTS
08/07/2025 - 8:48 AM
ACCELERATOR
MODEL
37.6
tokens/s
generation
1.80
sec
time to first token
760
tokens/s
prompt
251
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi2 - Q4_0
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
861
tokens/s
43.2
tokens/s
1.21
sec
pp4096+tg256
660
tokens/s
21.6
tokens/s
6.25
sec
pp2048+tg256
778
tokens/s
32.4
tokens/s
2.66
sec
pp2048+tg768
778
tokens/s
30.2
tokens/s
2.66
sec
pp1024+tg1024
845
tokens/s
38.2
tokens/s
1.23
sec
pp1280+tg3072
815
tokens/s
27.5
tokens/s
1.60
sec
pp384+tg1152
882
tokens/s
45.3
tokens/s
453
ms
pp64+tg1024
811
tokens/s
52.1
tokens/s
94
ms
pp16+tg1536
408
tokens/s
48.2
tokens/s
54
ms