TEST #2499 RESULTS
02/01/2026 - 10:52 AM
ACCELERATOR
MODEL
528
tokens/s
generation
49
ms
time to first token
34967
tokens/s
prompt
7240
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
43435
tokens/s
548
tokens/s
26
ms
pp4096+tg256
19316
tokens/s
477
tokens/s
215
ms
pp2048+tg256
33694
tokens/s
521
tokens/s
63
ms
pp2048+tg768
33671
tokens/s
525
tokens/s
63
ms
pp1024+tg1024
50780
tokens/s
529
tokens/s
22
ms
pp1280+tg3072
45875
tokens/s
511
tokens/s
30
ms
pp384+tg1152
67699
tokens/s
553
tokens/s
7
ms
pp64+tg1024
16357
tokens/s
539
tokens/s
5
ms
pp16+tg1536
3875
tokens/s
549
tokens/s
6
ms