TEST #1465 RESULTS
08/30/2025 - 8:02 PM
ACCELERATOR
MODEL
11.1
tokens/s
generation
30.39
sec
time to first token
41
tokens/s
prompt
25
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.7GB
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
46
tokens/s
12.0
tokens/s
22.38
sec
pp4096+tg256
43
tokens/s
10.5
tokens/s
94.57
sec
pp2048+tg256
46
tokens/s
10.8
tokens/s
44.39
sec
pp2048+tg768
46
tokens/s
11.4
tokens/s
45.09
sec
pp1024+tg1024
47
tokens/s
11.0
tokens/s
21.69
sec
pp1280+tg3072
39
tokens/s
10.6
tokens/s
32.98
sec
pp384+tg1152
39
tokens/s
11.7
tokens/s
9.92
sec
pp64+tg1024
36
tokens/s
11.3
tokens/s
1.88
sec
pp16+tg1536
31
tokens/s
10.9
tokens/s
603
ms