TEST #2389 RESULTS
01/30/2026 - 12:59 PM
ACCELERATOR
MODEL
908
tokens/s
generation
17
ms
time to first token
92104
tokens/s
prompt
17015
LocalScore
HOW YOU STACK UP
Explore All Resultsllama - all F32 (guessed)
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
127966
tokens/s
952
tokens/s
9
ms
pp4096+tg256
59841
tokens/s
904
tokens/s
70
ms
pp2048+tg256
103153
tokens/s
952
tokens/s
21
ms
pp2048+tg768
89420
tokens/s
905
tokens/s
24
ms
pp1024+tg1024
150548
tokens/s
878
tokens/s
8
ms
pp1280+tg3072
148334
tokens/s
917
tokens/s
10
ms
pp384+tg1152
110367
tokens/s
876
tokens/s
5
ms
pp64+tg1024
32777
tokens/s
889
tokens/s
3
ms
pp16+tg1536
6533
tokens/s
898
tokens/s
3
ms