TEST #2235 RESULTS
01/11/2026 - 4:52 AM
ACCELERATOR
MODEL
289
tokens/s
generation
1.11
sec
time to first token
1657
tokens/s
prompt
755
LocalScore
HOW YOU STACK UP
Explore All ResultsPythia 70m 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
1610
tokens/s
316
tokens/s
639
ms
pp4096+tg256
933
tokens/s
169
tokens/s
4.40
sec
pp2048+tg256
1279
tokens/s
268
tokens/s
1.60
sec
pp2048+tg768
1246
tokens/s
231
tokens/s
1.65
sec
pp1024+tg1024
1563
tokens/s
281
tokens/s
659
ms
pp1280+tg3072
1550
tokens/s
218
tokens/s
829
ms
pp384+tg1152
1984
tokens/s
349
tokens/s
196
ms
pp64+tg1024
2887
tokens/s
410
tokens/s
24
ms
pp16+tg1536
1863
tokens/s
361
tokens/s
11
ms