TEST #406 RESULTS
04/06/2025 - 7:02 PM
ACCELERATOR
MODEL
63.4
tokens/s
generation
610
ms
time to first token
2131
tokens/s
prompt
605
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.13.8-zen1-1.1-zen
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 ZEN SMP PREEMPT_DYNAMIC Mon, 24 Mar 2025 03:45:21 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2490
tokens/s
66.2
tokens/s
427
ms
pp4096+tg256
2057
tokens/s
56.9
tokens/s
2.01
sec
pp2048+tg256
2322
tokens/s
62.4
tokens/s
898
ms
pp2048+tg768
2247
tokens/s
61.7
tokens/s
928
ms
pp1024+tg1024
2506
tokens/s
64.3
tokens/s
424
ms
pp1280+tg3072
2426
tokens/s
60.4
tokens/s
543
ms
pp384+tg1152
2525
tokens/s
66.1
tokens/s
173
ms
pp64+tg1024
1982
tokens/s
67.4
tokens/s
46
ms
pp16+tg1536
628
tokens/s
65.4
tokens/s
39
ms