TEST #2077 RESULTS
01/02/2026 - 9:07 PM
ACCELERATOR
MODEL
13.4
tokens/s
generation
2.28
sec
time to first token
685
tokens/s
prompt
159
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 265H (arrowlake)
RAM
30.3GB
OS
Linux
Kernel Release
6.17.0-8-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #8-Ubuntu SMP PREEMPT_DYNAMIC Fri Nov 14 21:44:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
768
tokens/s
16.3
tokens/s
1.46
sec
pp4096+tg256
540
tokens/s
8.8
tokens/s
7.69
sec
pp2048+tg256
599
tokens/s
12.8
tokens/s
3.52
sec
pp2048+tg768
601
tokens/s
11.9
tokens/s
3.51
sec
pp1024+tg1024
740
tokens/s
14.8
tokens/s
1.48
sec
pp1280+tg3072
643
tokens/s
10.5
tokens/s
2.09
sec
pp384+tg1152
722
tokens/s
15.1
tokens/s
629
ms
pp64+tg1024
1086
tokens/s
15.4
tokens/s
93
ms
pp16+tg1536
468
tokens/s
15.1
tokens/s
73
ms