TEST #2528 RESULTS
02/03/2026 - 11:21 PM
ACCELERATOR
MODEL
30.1
tokens/s
generation
1.93
sec
time to first token
1132
tokens/s
prompt
260
LocalScore
HOW YOU STACK UP
Explore All ResultsNemotron Cascade 8B - 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
1354
tokens/s
30.7
tokens/s
789
ms
pp4096+tg256
369
tokens/s
27.1
tokens/s
11.15
sec
pp2048+tg256
1253
tokens/s
30.0
tokens/s
1.67
sec
pp2048+tg768
1280
tokens/s
29.4
tokens/s
1.63
sec
pp1024+tg1024
1411
tokens/s
30.6
tokens/s
757
ms
pp1280+tg3072
1368
tokens/s
29.0
tokens/s
968
ms
pp384+tg1152
1559
tokens/s
31.1
tokens/s
279
ms
pp64+tg1024
1244
tokens/s
31.5
tokens/s
83
ms
pp16+tg1536
355
tokens/s
31.2
tokens/s
76
ms