TEST #2727 RESULTS
02/18/2026 - 12:00 AM
ACCELERATOR
MODEL
844
tokens/s
generation
19
ms
time to first token
87067
tokens/s
prompt
15700
LocalScore
HOW YOU STACK UP
Explore All Resultsllama - 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
124491
tokens/s
826
tokens/s
9
ms
pp4096+tg256
56825
tokens/s
787
tokens/s
74
ms
pp2048+tg256
96789
tokens/s
820
tokens/s
22
ms
pp2048+tg768
97817
tokens/s
863
tokens/s
22
ms
pp1024+tg1024
141744
tokens/s
867
tokens/s
9
ms
pp1280+tg3072
124805
tokens/s
829
tokens/s
12
ms
pp384+tg1152
129315
tokens/s
857
tokens/s
6
ms
pp64+tg1024
5798
tokens/s
864
tokens/s
13
ms
pp16+tg1536
6022
tokens/s
886
tokens/s
4
ms