TEST #334 RESULTS
04/06/2025 - 1:11 AM
ACCELERATOR
MODEL
33.1
tokens/s
generation
1.40
sec
time to first token
1016
tokens/s
prompt
289
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q6_K
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
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
1163
tokens/s
39.6
tokens/s
905
ms
pp4096+tg256
790
tokens/s
6.6
tokens/s
5.33
sec
pp2048+tg256
1051
tokens/s
31.7
tokens/s
1.98
sec
pp2048+tg768
1057
tokens/s
30.4
tokens/s
1.97
sec
pp1024+tg1024
1237
tokens/s
36.1
tokens/s
853
ms
pp1280+tg3072
1195
tokens/s
21.6
tokens/s
1.10
sec
pp384+tg1152
1360
tokens/s
41.4
tokens/s
303
ms
pp64+tg1024
752
tokens/s
46.5
tokens/s
104
ms
pp16+tg1536
537
tokens/s
44.3
tokens/s
48
ms