TEST #662 RESULTS
04/10/2025 - 12:30 AM
ACCELERATOR
MODEL
58.6
tokens/s
generation
657
ms
time to first token
1962
tokens/s
prompt
559
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
15.6GB
OS
Linux
Kernel Release
5.15.167.4-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Tue Nov 5 00:21:55 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2343
tokens/s
60.8
tokens/s
453
ms
pp4096+tg256
1861
tokens/s
58.1
tokens/s
2.22
sec
pp2048+tg256
2217
tokens/s
60.7
tokens/s
940
ms
pp2048+tg768
2165
tokens/s
60.7
tokens/s
962
ms
pp1024+tg1024
2293
tokens/s
58.5
tokens/s
464
ms
pp1280+tg3072
2209
tokens/s
58.0
tokens/s
596
ms
pp384+tg1152
2375
tokens/s
51.1
tokens/s
179
ms
pp64+tg1024
1700
tokens/s
61.3
tokens/s
54
ms
pp16+tg1536
490
tokens/s
58.2
tokens/s
50
ms