TEST #767 RESULTS
04/25/2025 - 8:50 PM
ACCELERATOR
MODEL
30.0
tokens/s
generation
8.22
sec
time to first token
891
tokens/s
prompt
148
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
15.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
84
tokens/s
9.9
tokens/s
12.29
sec
pp4096+tg256
73
tokens/s
3.3
tokens/s
56.34
sec
pp2048+tg256
1341
tokens/s
42.0
tokens/s
1.55
sec
pp2048+tg768
1336
tokens/s
41.4
tokens/s
1.56
sec
pp1024+tg1024
1447
tokens/s
43.2
tokens/s
730
ms
pp1280+tg3072
1336
tokens/s
31.7
tokens/s
981
ms
pp384+tg1152
1144
tokens/s
35.3
tokens/s
363
ms
pp64+tg1024
963
tokens/s
32.0
tokens/s
94
ms
pp16+tg1536
297
tokens/s
31.2
tokens/s
81
ms