TEST #1463 RESULTS
08/30/2025 - 5:32 PM
ACCELERATOR
MODEL
41.2
tokens/s
generation
1.14
sec
time to first token
1096
tokens/s
prompt
341
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12600K (alderlake)
RAM
47.8GB
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
1325
tokens/s
47.1
tokens/s
793
ms
pp4096+tg256
1121
tokens/s
37.3
tokens/s
3.68
sec
pp2048+tg256
1226
tokens/s
42.0
tokens/s
1.69
sec
pp2048+tg768
1212
tokens/s
40.5
tokens/s
1.71
sec
pp1024+tg1024
1267
tokens/s
41.9
tokens/s
830
ms
pp1280+tg3072
1209
tokens/s
36.9
tokens/s
1.08
sec
pp384+tg1152
1262
tokens/s
41.1
tokens/s
328
ms
pp64+tg1024
970
tokens/s
42.0
tokens/s
90
ms
pp16+tg1536
268
tokens/s
42.0
tokens/s
81
ms