TEST #3337 RESULTS
04/16/2026 - 10:02 PM
ACCELERATOR
MODEL
8.3
tokens/s
generation
30.04
sec
time to first token
48
tokens/s
prompt
24
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.17.0-20-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #20~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Mar 19 01:28:37 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
48
tokens/s
8.3
tokens/s
21.25
sec
pp4096+tg256
42
tokens/s
7.2
tokens/s
98.36
sec
pp2048+tg256
46
tokens/s
8.2
tokens/s
44.59
sec
pp2048+tg768
45
tokens/s
8.2
tokens/s
45.22
sec
pp1024+tg1024
46
tokens/s
8.3
tokens/s
22.30
sec
pp1280+tg3072
44
tokens/s
7.9
tokens/s
29.52
sec
pp384+tg1152
53
tokens/s
8.9
tokens/s
7.39
sec
pp64+tg1024
54
tokens/s
9.1
tokens/s
1.29
sec
pp16+tg1536
52
tokens/s
9.0
tokens/s
414
ms