TEST #532 RESULTS
04/07/2025 - 9:30 PM
ACCELERATOR
MODEL
103
tokens/s
generation
180
ms
time to first token
7398
tokens/s
prompt
1617
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
63.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9306
tokens/s
100
tokens/s
120
ms
pp4096+tg256
6758
tokens/s
99.7
tokens/s
616
ms
pp2048+tg256
8259
tokens/s
103
tokens/s
258
ms
pp2048+tg768
8265
tokens/s
104
tokens/s
258
ms
pp1024+tg1024
9450
tokens/s
103
tokens/s
119
ms
pp1280+tg3072
9138
tokens/s
101
tokens/s
150
ms
pp384+tg1152
9706
tokens/s
103
tokens/s
50
ms
pp64+tg1024
4487
tokens/s
105
tokens/s
23
ms
pp16+tg1536
1219
tokens/s
104
tokens/s
22
ms