TEST #2489 RESULTS
02/01/2026 - 10:44 AM
ACCELERATOR
MODEL
469
tokens/s
generation
15
ms
time to first token
95601
tokens/s
prompt
14289
LocalScore
HOW YOU STACK UP
Explore All ResultsConfig.Json - Q8_0
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
117117
tokens/s
433
tokens/s
11
ms
pp4096+tg256
106263
tokens/s
457
tokens/s
41
ms
pp2048+tg256
132395
tokens/s
477
tokens/s
18
ms
pp2048+tg768
132815
tokens/s
471
tokens/s
17
ms
pp1024+tg1024
125047
tokens/s
476
tokens/s
10
ms
pp1280+tg3072
142653
tokens/s
467
tokens/s
11
ms
pp384+tg1152
80338
tokens/s
479
tokens/s
7
ms
pp64+tg1024
18675
tokens/s
480
tokens/s
18
ms
pp16+tg1536
5108
tokens/s
479
tokens/s
5
ms