TEST #2728 RESULTS
02/18/2026 - 12:00 AM
ACCELERATOR
MODEL
846
tokens/s
generation
21
ms
time to first token
79711
tokens/s
prompt
14849
LocalScore
HOW YOU STACK UP
Explore All Resultsllama - Q6_K
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
111020
tokens/s
751
tokens/s
11
ms
pp4096+tg256
48069
tokens/s
786
tokens/s
87
ms
pp2048+tg256
90090
tokens/s
861
tokens/s
24
ms
pp2048+tg768
100040
tokens/s
858
tokens/s
22
ms
pp1024+tg1024
131289
tokens/s
879
tokens/s
9
ms
pp1280+tg3072
115491
tokens/s
823
tokens/s
13
ms
pp384+tg1152
108616
tokens/s
881
tokens/s
5
ms
pp64+tg1024
6136
tokens/s
871
tokens/s
12
ms
pp16+tg1536
6653
tokens/s
905
tokens/s
4
ms