TEST #658 RESULTS
04/10/2025 - 12:03 AM
ACCELERATOR
MODEL
103
tokens/s
generation
352
ms
time to first token
3637
tokens/s
prompt
1020
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.2GB
OS
Linux
Kernel Release
6.11.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 24 16:52:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4377
tokens/s
106
tokens/s
243
ms
pp4096+tg256
3500
tokens/s
92.7
tokens/s
1.18
sec
pp2048+tg256
4036
tokens/s
102
tokens/s
517
ms
pp2048+tg768
4036
tokens/s
100
tokens/s
517
ms
pp1024+tg1024
4388
tokens/s
104
tokens/s
243
ms
pp1280+tg3072
4256
tokens/s
98.5
tokens/s
312
ms
pp384+tg1152
4570
tokens/s
106
tokens/s
93
ms
pp64+tg1024
2792
tokens/s
109
tokens/s
32
ms
pp16+tg1536
778
tokens/s
107
tokens/s
29
ms