TEST #3401 RESULTS
04/27/2026 - 7:05 AM
ACCELERATOR
MODEL
4.7
tokens/s
generation
3.42
sec
time to first token
415
tokens/s
prompt
83
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 8600G w/ Radeon 760M Graphics (znver4)
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
486
tokens/s
5.3
tokens/s
2.29
sec
pp4096+tg256
371
tokens/s
1.2
tokens/s
11.91
sec
pp2048+tg256
437
tokens/s
3.6
tokens/s
5.00
sec
pp2048+tg768
434
tokens/s
3.2
tokens/s
5.03
sec
pp1024+tg1024
478
tokens/s
4.7
tokens/s
2.33
sec
pp1280+tg3072
458
tokens/s
2.5
tokens/s
3.01
sec
pp384+tg1152
528
tokens/s
6.4
tokens/s
842
ms
pp64+tg1024
393
tokens/s
8.4
tokens/s
241
ms
pp16+tg1536
152
tokens/s
7.2
tokens/s
174
ms