TEST #1092 RESULTS
06/23/2025 - 9:20 AM
ACCELERATOR
MODEL
85.4
tokens/s
generation
329
ms
time to first token
3876
tokens/s
prompt
1002
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
53.6GB
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
4755
tokens/s
87.6
tokens/s
227
ms
pp4096+tg256
3806
tokens/s
83.5
tokens/s
1.10
sec
pp2048+tg256
4452
tokens/s
86.4
tokens/s
471
ms
pp2048+tg768
4439
tokens/s
85.0
tokens/s
473
ms
pp1024+tg1024
4760
tokens/s
86.3
tokens/s
227
ms
pp1280+tg3072
4485
tokens/s
85.4
tokens/s
297
ms
pp384+tg1152
4672
tokens/s
86.4
tokens/s
94
ms
pp64+tg1024
2848
tokens/s
84.3
tokens/s
34
ms
pp16+tg1536
665
tokens/s
84.0
tokens/s
36
ms