TEST #314 RESULTS
04/05/2025 - 11:44 PM
ACCELERATOR
MODEL
11.7
tokens/s
generation
1.88
sec
time to first token
690
tokens/s
prompt
162
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7940HS w/ Radeon 780M Graphics (znver4)
RAM
54.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
919
tokens/s
12.4
tokens/s
1.19
sec
pp4096+tg256
650
tokens/s
3.7
tokens/s
6.56
sec
pp2048+tg256
799
tokens/s
8.4
tokens/s
2.70
sec
pp2048+tg768
789
tokens/s
7.6
tokens/s
2.73
sec
pp1024+tg1024
864
tokens/s
11.0
tokens/s
1.27
sec
pp1280+tg3072
834
tokens/s
6.5
tokens/s
1.63
sec
pp384+tg1152
849
tokens/s
15.6
tokens/s
495
ms
pp64+tg1024
305
tokens/s
21.7
tokens/s
237
ms
pp16+tg1536
206
tokens/s
17.8
tokens/s
110
ms