TEST #2233 RESULTS
01/11/2026 - 4:51 AM
ACCELERATOR
MODEL
65.9
tokens/s
generation
3.51
sec
time to first token
493
tokens/s
prompt
210
LocalScore
HOW YOU STACK UP
Explore All ResultsPythia 160m Deduped - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i3-1215U (alderlake)
RAM
11.7GB
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
490
tokens/s
80.3
tokens/s
2.10
sec
pp4096+tg256
312
tokens/s
29.0
tokens/s
13.16
sec
pp2048+tg256
396
tokens/s
47.5
tokens/s
5.19
sec
pp2048+tg768
381
tokens/s
44.0
tokens/s
5.39
sec
pp1024+tg1024
492
tokens/s
62.1
tokens/s
2.09
sec
pp1280+tg3072
445
tokens/s
39.4
tokens/s
2.89
sec
pp384+tg1152
569
tokens/s
87.0
tokens/s
682
ms
pp64+tg1024
676
tokens/s
109
tokens/s
99
ms
pp16+tg1536
671
tokens/s
95.2
tokens/s
29
ms