TEST #2427 RESULTS
01/31/2026 - 3:42 PM
ACCELERATOR
MODEL
605
tokens/s
generation
38
ms
time to first token
40369
tokens/s
prompt
8647
LocalScore
HOW YOU STACK UP
Explore All ResultsDistilgpt2 Tiny Conversational - Q6_K
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
46688
tokens/s
512
tokens/s
24
ms
pp4096+tg256
27040
tokens/s
530
tokens/s
154
ms
pp2048+tg256
43274
tokens/s
602
tokens/s
49
ms
pp2048+tg768
43888
tokens/s
614
tokens/s
48
ms
pp1024+tg1024
57664
tokens/s
634
tokens/s
19
ms
pp1280+tg3072
53314
tokens/s
589
tokens/s
26
ms
pp384+tg1152
66683
tokens/s
656
tokens/s
7
ms
pp64+tg1024
22364
tokens/s
665
tokens/s
4
ms
pp16+tg1536
2405
tokens/s
645
tokens/s
9
ms