TEST #3683 RESULTS
06/03/2026 - 4:04 PM
ACCELERATOR
MODEL
10.9
tokens/s
generation
16.99
sec
time to first token
81
tokens/s
prompt
37
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7940HS w/ Radeon 780M Graphics (znver4)
RAM
60.6GB
OS
Linux
Kernel Release
7.0.10-201.fc44.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed May 27 13:57:41 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
83
tokens/s
11.3
tokens/s
12.37
sec
pp4096+tg256
75
tokens/s
9.8
tokens/s
55.00
sec
pp2048+tg256
80
tokens/s
10.7
tokens/s
25.83
sec
pp2048+tg768
80
tokens/s
10.5
tokens/s
25.81
sec
pp1024+tg1024
83
tokens/s
11.0
tokens/s
12.48
sec
pp1280+tg3072
82
tokens/s
10.3
tokens/s
15.61
sec
pp384+tg1152
83
tokens/s
11.3
tokens/s
4.73
sec
pp64+tg1024
85
tokens/s
11.5
tokens/s
833
ms
pp16+tg1536
75
tokens/s
11.4
tokens/s
295
ms