TEST #2412 RESULTS
01/31/2026 - 6:37 AM
ACCELERATOR
MODEL
42.5
tokens/s
generation
352
ms
time to first token
3838
tokens/s
prompt
773
LocalScore
HOW YOU STACK UP
Explore All ResultsSyngen Reasoning 0.6b - BF16
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
5151
tokens/s
44.3
tokens/s
222
ms
pp4096+tg256
3363
tokens/s
39.5
tokens/s
1.24
sec
pp2048+tg256
4402
tokens/s
42.4
tokens/s
489
ms
pp2048+tg768
4409
tokens/s
41.9
tokens/s
488
ms
pp1024+tg1024
5091
tokens/s
43.2
tokens/s
224
ms
pp1280+tg3072
4777
tokens/s
40.7
tokens/s
292
ms
pp384+tg1152
5333
tokens/s
43.4
tokens/s
96
ms
pp64+tg1024
1505
tokens/s
43.5
tokens/s
65
ms
pp16+tg1536
513
tokens/s
43.2
tokens/s
54
ms