TEST #434 RESULTS
04/06/2025 - 9:45 PM
ACCELERATOR
MODEL
44.5
tokens/s
generation
1.12
sec
time to first token
1201
tokens/s
prompt
363
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q6_K
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
1436
tokens/s
50.8
tokens/s
733
ms
pp4096+tg256
1040
tokens/s
26.8
tokens/s
3.98
sec
pp2048+tg256
1262
tokens/s
42.5
tokens/s
1.65
sec
pp2048+tg768
1260
tokens/s
41.0
tokens/s
1.65
sec
pp1024+tg1024
1404
tokens/s
47.1
tokens/s
749
ms
pp1280+tg3072
1386
tokens/s
35.9
tokens/s
944
ms
pp384+tg1152
1511
tokens/s
50.9
tokens/s
273
ms
pp64+tg1024
951
tokens/s
53.5
tokens/s
85
ms
pp16+tg1536
562
tokens/s
52.1
tokens/s
46
ms