TEST #431 RESULTS
04/06/2025 - 9:37 PM
ACCELERATOR
MODEL
50.3
tokens/s
generation
1.13
sec
time to first token
1170
tokens/s
prompt
373
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
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
1302
tokens/s
56.0
tokens/s
804
ms
pp4096+tg256
1037
tokens/s
28.6
tokens/s
3.98
sec
pp2048+tg256
1267
tokens/s
47.7
tokens/s
1.64
sec
pp2048+tg768
1261
tokens/s
45.7
tokens/s
1.64
sec
pp1024+tg1024
1405
tokens/s
53.6
tokens/s
746
ms
pp1280+tg3072
1391
tokens/s
39.6
tokens/s
938
ms
pp384+tg1152
1475
tokens/s
58.7
tokens/s
276
ms
pp64+tg1024
802
tokens/s
62.4
tokens/s
95
ms
pp16+tg1536
588
tokens/s
60.1
tokens/s
42
ms