TEST #437 RESULTS
04/06/2025 - 10:00 PM
ACCELERATOR
MODEL
17.7
tokens/s
generation
1.05
sec
time to first token
1243
tokens/s
prompt
276
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - F16
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
1671
tokens/s
18.7
tokens/s
666
ms
pp4096+tg256
1148
tokens/s
14.1
tokens/s
3.64
sec
pp2048+tg256
1438
tokens/s
17.6
tokens/s
1.48
sec
pp2048+tg768
1441
tokens/s
17.4
tokens/s
1.48
sec
pp1024+tg1024
1627
tokens/s
18.3
tokens/s
683
ms
pp1280+tg3072
1576
tokens/s
16.3
tokens/s
866
ms
pp384+tg1152
1577
tokens/s
18.8
tokens/s
296
ms
pp64+tg1024
552
tokens/s
19.2
tokens/s
167
ms
pp16+tg1536
154
tokens/s
19.0
tokens/s
155
ms