TEST #3146 RESULTS
03/21/2026 - 6:18 PM
ACCELERATOR
MODEL
45.4
tokens/s
generation
621
ms
time to first token
2224
tokens/s
prompt
546
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400F (alderlake)
RAM
15.8GB
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
2661
tokens/s
45.8
tokens/s
407
ms
pp4096+tg256
1887
tokens/s
42.9
tokens/s
2.19
sec
pp2048+tg256
2342
tokens/s
45.3
tokens/s
897
ms
pp2048+tg768
2338
tokens/s
45.1
tokens/s
898
ms
pp1024+tg1024
2512
tokens/s
45.9
tokens/s
430
ms
pp1280+tg3072
2603
tokens/s
44.7
tokens/s
513
ms
pp384+tg1152
3052
tokens/s
45.9
tokens/s
147
ms
pp64+tg1024
2016
tokens/s
46.4
tokens/s
53
ms
pp16+tg1536
603
tokens/s
46.3
tokens/s
48
ms