TEST #2456 RESULTS
02/01/2026 - 5:58 AM
ACCELERATOR
MODEL
519
tokens/s
generation
50
ms
time to first token
33597
tokens/s
prompt
7038
LocalScore
HOW YOU STACK UP
Explore All ResultsTinyLLama v0 - 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
42939
tokens/s
542
tokens/s
26
ms
pp4096+tg256
19189
tokens/s
492
tokens/s
216
ms
pp2048+tg256
34107
tokens/s
516
tokens/s
62
ms
pp2048+tg768
29598
tokens/s
518
tokens/s
72
ms
pp1024+tg1024
39433
tokens/s
519
tokens/s
28
ms
pp1280+tg3072
45355
tokens/s
509
tokens/s
30
ms
pp384+tg1152
70990
tokens/s
533
tokens/s
7
ms
pp64+tg1024
15900
tokens/s
528
tokens/s
6
ms
pp16+tg1536
4864
tokens/s
517
tokens/s
5
ms