TEST #3315 RESULTS
04/15/2026 - 2:28 PM
ACCELERATOR
MODEL
58.5
tokens/s
generation
685
ms
time to first token
1910
tokens/s
prompt
546
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
2248
tokens/s
62.3
tokens/s
471
ms
pp4096+tg256
1795
tokens/s
54.6
tokens/s
2.30
sec
pp2048+tg256
2083
tokens/s
59.0
tokens/s
1.00
sec
pp2048+tg768
2062
tokens/s
58.2
tokens/s
1.01
sec
pp1024+tg1024
2223
tokens/s
59.4
tokens/s
477
ms
pp1280+tg3072
2113
tokens/s
55.1
tokens/s
622
ms
pp384+tg1152
2236
tokens/s
59.0
tokens/s
188
ms
pp64+tg1024
1885
tokens/s
60.4
tokens/s
50
ms
pp16+tg1536
544
tokens/s
58.7
tokens/s
46
ms