TEST #978 RESULTS
06/03/2025 - 2:33 AM
ACCELERATOR
MODEL
26.0
tokens/s
generation
2.32
sec
time to first token
760
tokens/s
prompt
204
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-4590 CPU @ 3.30GHz (haswell)
RAM
31.9GB
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
938
tokens/s
27.1
tokens/s
1.13
sec
pp4096+tg256
355
tokens/s
23.2
tokens/s
11.59
sec
pp2048+tg256
856
tokens/s
25.9
tokens/s
2.43
sec
pp2048+tg768
859
tokens/s
25.6
tokens/s
2.42
sec
pp1024+tg1024
923
tokens/s
26.5
tokens/s
1.15
sec
pp1280+tg3072
898
tokens/s
25.1
tokens/s
1.46
sec
pp384+tg1152
1005
tokens/s
26.9
tokens/s
421
ms
pp64+tg1024
794
tokens/s
26.9
tokens/s
117
ms
pp16+tg1536
211
tokens/s
26.9
tokens/s
113
ms