TEST #2407 RESULTS
01/31/2026 - 6:27 AM
ACCELERATOR
MODEL
2811
tokens/s
generation
6
ms
time to first token
218864
tokens/s
prompt
46168
LocalScore
HOW YOU STACK UP
Explore All ResultsPlanck-OpenLAiNN-10M - F16
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
261899
tokens/s
2808
tokens/s
4
ms
pp4096+tg256
178334
tokens/s
2287
tokens/s
23
ms
pp2048+tg256
269364
tokens/s
2645
tokens/s
8
ms
pp2048+tg768
283202
tokens/s
2549
tokens/s
8
ms
pp1024+tg1024
327115
tokens/s
3033
tokens/s
3
ms
pp1280+tg3072
311413
tokens/s
2664
tokens/s
5
ms
pp384+tg1152
270823
tokens/s
3053
tokens/s
2
ms
pp64+tg1024
54371
tokens/s
3157
tokens/s
2
ms
pp16+tg1536
13252
tokens/s
3104
tokens/s
2
ms