TEST #324 RESULTS
04/06/2025 - 12:23 AM
ACCELERATOR
MODEL
6.4
tokens/s
generation
4.58
sec
time to first token
288
tokens/s
prompt
74
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B 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
346
tokens/s
7.2
tokens/s
3.10
sec
pp4096+tg256
280
tokens/s
0.9
tokens/s
15.74
sec
pp2048+tg256
316
tokens/s
5.1
tokens/s
6.71
sec
pp2048+tg768
318
tokens/s
4.6
tokens/s
6.66
sec
pp1024+tg1024
342
tokens/s
6.4
tokens/s
3.14
sec
pp1280+tg3072
328
tokens/s
2.9
tokens/s
4.06
sec
pp384+tg1152
357
tokens/s
8.8
tokens/s
1.16
sec
pp64+tg1024
141
tokens/s
11.8
tokens/s
510
ms
pp16+tg1536
162
tokens/s
10.0
tokens/s
150
ms