TEST #2504 RESULTS
02/01/2026 - 11:16 PM
ACCELERATOR
MODEL
1375
tokens/s
generation
15
ms
time to first token
90490
tokens/s
prompt
20022
LocalScore
HOW YOU STACK UP
Explore All Resultsvicuna-68m - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
117328
tokens/s
1111
tokens/s
10
ms
pp4096+tg256
69526
tokens/s
1168
tokens/s
60
ms
pp2048+tg256
119668
tokens/s
1314
tokens/s
18
ms
pp2048+tg768
115790
tokens/s
1378
tokens/s
18
ms
pp1024+tg1024
146673
tokens/s
1467
tokens/s
8
ms
pp1280+tg3072
83719
tokens/s
1321
tokens/s
16
ms
pp384+tg1152
117485
tokens/s
1536
tokens/s
4
ms
pp64+tg1024
36103
tokens/s
1541
tokens/s
2
ms
pp16+tg1536
8115
tokens/s
1536
tokens/s
3
ms