TEST #2470 RESULTS
02/01/2026 - 10:35 AM
ACCELERATOR
MODEL
469
tokens/s
generation
56
ms
time to first token
29126
tokens/s
prompt
6257
LocalScore
HOW YOU STACK UP
Explore All ResultsLite-Oute-1-65M-Instruct - Q4_K - Medium
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
36291
tokens/s
465
tokens/s
30
ms
pp4096+tg256
18482
tokens/s
431
tokens/s
224
ms
pp2048+tg256
25336
tokens/s
482
tokens/s
84
ms
pp2048+tg768
30396
tokens/s
459
tokens/s
69
ms
pp1024+tg1024
44424
tokens/s
470
tokens/s
26
ms
pp1280+tg3072
33004
tokens/s
465
tokens/s
41
ms
pp384+tg1152
62283
tokens/s
478
tokens/s
11
ms
pp64+tg1024
8000
tokens/s
487
tokens/s
10
ms
pp16+tg1536
3916
tokens/s
480
tokens/s
7
ms