TEST #421 RESULTS
04/06/2025 - 8:13 PM
ACCELERATOR
MODEL
113
tokens/s
generation
326
ms
time to first token
3991
tokens/s
prompt
1113
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.13.8-zen1-1.1-zen
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 ZEN SMP PREEMPT_DYNAMIC Mon, 24 Mar 2025 03:45:21 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4691
tokens/s
116
tokens/s
227
ms
pp4096+tg256
3770
tokens/s
102
tokens/s
1.10
sec
pp2048+tg256
4346
tokens/s
112
tokens/s
480
ms
pp2048+tg768
4346
tokens/s
110
tokens/s
480
ms
pp1024+tg1024
4692
tokens/s
114
tokens/s
227
ms
pp1280+tg3072
4570
tokens/s
108
tokens/s
289
ms
pp384+tg1152
5097
tokens/s
116
tokens/s
84
ms
pp64+tg1024
3481
tokens/s
119
tokens/s
26
ms
pp16+tg1536
923
tokens/s
118
tokens/s
25
ms