TEST #2405 RESULTS
01/30/2026 - 9:22 PM
ACCELERATOR
MODEL
22.7
tokens/s
generation
4.31
sec
time to first token
301
tokens/s
prompt
117
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
365
tokens/s
27.2
tokens/s
2.85
sec
pp4096+tg256
283
tokens/s
12.0
tokens/s
14.56
sec
pp2048+tg256
327
tokens/s
20.9
tokens/s
6.30
sec
pp2048+tg768
325
tokens/s
19.4
tokens/s
6.35
sec
pp1024+tg1024
346
tokens/s
23.2
tokens/s
3.00
sec
pp1280+tg3072
324
tokens/s
17.1
tokens/s
3.99
sec
pp384+tg1152
336
tokens/s
26.5
tokens/s
1.17
sec
pp64+tg1024
139
tokens/s
30.1
tokens/s
489
ms
pp16+tg1536
265
tokens/s
28.1
tokens/s
88
ms