TEST #170 RESULTS
03/30/2025 - 8:09 PM
ACCELERATOR
MODEL
106
tokens/s
generation
161
ms
time to first token
8441
tokens/s
prompt
1772
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
125.7GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11011
tokens/s
121
tokens/s
101
ms
pp4096+tg256
7754
tokens/s
71.8
tokens/s
542
ms
pp2048+tg256
9765
tokens/s
98.6
tokens/s
220
ms
pp2048+tg768
9736
tokens/s
92.6
tokens/s
221
ms
pp1024+tg1024
11134
tokens/s
108
tokens/s
100
ms
pp1280+tg3072
10409
tokens/s
86.8
tokens/s
132
ms
pp384+tg1152
11160
tokens/s
121
tokens/s
42
ms
pp64+tg1024
4766
tokens/s
131
tokens/s
20
ms
pp16+tg1536
237
tokens/s
126
tokens/s
74
ms