TEST #2575 RESULTS
02/10/2026 - 9:05 AM
ACCELERATOR
MODEL
323
tokens/s
generation
67
ms
time to first token
22273
tokens/s
prompt
4752
LocalScore
HOW YOU STACK UP
Explore All ResultsPythia 160m Deduped - 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
25895
tokens/s
305
tokens/s
43
ms
pp4096+tg256
16442
tokens/s
290
tokens/s
253
ms
pp2048+tg256
23756
tokens/s
305
tokens/s
89
ms
pp2048+tg768
23738
tokens/s
318
tokens/s
90
ms
pp1024+tg1024
31129
tokens/s
332
tokens/s
36
ms
pp1280+tg3072
28430
tokens/s
316
tokens/s
48
ms
pp384+tg1152
35951
tokens/s
339
tokens/s
14
ms
pp64+tg1024
13060
tokens/s
347
tokens/s
20
ms
pp16+tg1536
2056
tokens/s
353
tokens/s
11
ms