TEST #2454 RESULTS
02/01/2026 - 5:57 AM
ACCELERATOR
MODEL
414
tokens/s
generation
26
ms
time to first token
57990
tokens/s
prompt
9729
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi 3 Mini 4k Instruct - 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
74061
tokens/s
413
tokens/s
16
ms
pp4096+tg256
46515
tokens/s
374
tokens/s
91
ms
pp2048+tg256
72369
tokens/s
435
tokens/s
31
ms
pp2048+tg768
72659
tokens/s
417
tokens/s
30
ms
pp1024+tg1024
77023
tokens/s
418
tokens/s
15
ms
pp1280+tg3072
86437
tokens/s
391
tokens/s
17
ms
pp384+tg1152
76135
tokens/s
412
tokens/s
21
ms
pp64+tg1024
12709
tokens/s
427
tokens/s
7
ms
pp16+tg1536
4006
tokens/s
438
tokens/s
6
ms