TEST #2411 RESULTS
01/31/2026 - 6:31 AM
ACCELERATOR
MODEL
66.2
tokens/s
generation
474
ms
time to first token
2472
tokens/s
prompt
701
LocalScore
HOW YOU STACK UP
Explore All ResultsFijik1.5 2.6b A380M - 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
3215
tokens/s
63.6
tokens/s
335
ms
pp4096+tg256
2809
tokens/s
65.6
tokens/s
1.47
sec
pp2048+tg256
3017
tokens/s
63.2
tokens/s
695
ms
pp2048+tg768
3091
tokens/s
64.3
tokens/s
679
ms
pp1024+tg1024
3236
tokens/s
63.3
tokens/s
333
ms
pp1280+tg3072
3107
tokens/s
65.0
tokens/s
427
ms
pp384+tg1152
2775
tokens/s
69.4
tokens/s
154
ms
pp64+tg1024
712
tokens/s
70.0
tokens/s
105
ms
pp16+tg1536
286
tokens/s
71.0
tokens/s
68
ms