TEST #2234 RESULTS
01/11/2026 - 4:52 AM
ACCELERATOR
MODEL
295
tokens/s
generation
973
ms
time to first token
1887
tokens/s
prompt
830
LocalScore
HOW YOU STACK UP
Explore All ResultsPythia 70m Deduped v0 - 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
1856
tokens/s
378
tokens/s
555
ms
pp4096+tg256
1062
tokens/s
104
tokens/s
3.87
sec
pp2048+tg256
1469
tokens/s
243
tokens/s
1.40
sec
pp2048+tg768
1449
tokens/s
229
tokens/s
1.42
sec
pp1024+tg1024
1755
tokens/s
298
tokens/s
586
ms
pp1280+tg3072
1771
tokens/s
170
tokens/s
726
ms
pp384+tg1152
2284
tokens/s
378
tokens/s
170
ms
pp64+tg1024
2941
tokens/s
449
tokens/s
24
ms
pp16+tg1536
2396
tokens/s
402
tokens/s
9
ms