TEST #659 RESULTS
04/10/2025 - 12:07 AM
ACCELERATOR
MODEL
59.6
tokens/s
generation
631
ms
time to first token
2049
tokens/s
prompt
578
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.2GB
OS
Linux
Kernel Release
6.11.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 24 16:52:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2424
tokens/s
61.9
tokens/s
439
ms
pp4096+tg256
1976
tokens/s
53.5
tokens/s
2.09
sec
pp2048+tg256
2235
tokens/s
58.8
tokens/s
933
ms
pp2048+tg768
2234
tokens/s
57.8
tokens/s
934
ms
pp1024+tg1024
2434
tokens/s
60.4
tokens/s
437
ms
pp1280+tg3072
2352
tokens/s
56.3
tokens/s
561
ms
pp384+tg1152
2498
tokens/s
62.0
tokens/s
185
ms
pp64+tg1024
1766
tokens/s
62.8
tokens/s
51
ms
pp16+tg1536
519
tokens/s
62.6
tokens/s
47
ms