TEST #2798 RESULTS
02/23/2026 - 3:53 AM
ACCELERATOR
MODEL
45.8
tokens/s
generation
827
ms
time to first token
1785
tokens/s
prompt
462
LocalScore
HOW YOU STACK UP
Explore All ResultsRio 3.0 Open Mini - 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
2077
tokens/s
48.0
tokens/s
514
ms
pp4096+tg256
1348
tokens/s
39.8
tokens/s
3.06
sec
pp2048+tg256
1734
tokens/s
44.9
tokens/s
1.20
sec
pp2048+tg768
1740
tokens/s
44.1
tokens/s
1.20
sec
pp1024+tg1024
2061
tokens/s
46.5
tokens/s
518
ms
pp1280+tg3072
1961
tokens/s
43.0
tokens/s
673
ms
pp384+tg1152
2487
tokens/s
48.1
tokens/s
175
ms
pp64+tg1024
1997
tokens/s
48.9
tokens/s
52
ms
pp16+tg1536
661
tokens/s
48.8
tokens/s
44
ms