TEST #3267 RESULTS
04/09/2026 - 7:06 PM
ACCELERATOR
MODEL
20.0
tokens/s
generation
2.46
sec
time to first token
522
tokens/s
prompt
162
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 3 3100 4-Core Processor (znver2)
RAM
31.2GB
OS
Linux
Kernel Release
6.18.7-76061807-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202601231045~1769703228~24.04~cb87b5b SMP PREEMPT_DYNAMIC Thu J
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
594
tokens/s
22.2
tokens/s
1.77
sec
pp4096+tg256
516
tokens/s
18.5
tokens/s
7.99
sec
pp2048+tg256
572
tokens/s
20.5
tokens/s
3.63
sec
pp2048+tg768
564
tokens/s
19.9
tokens/s
3.68
sec
pp1024+tg1024
585
tokens/s
20.3
tokens/s
1.79
sec
pp1280+tg3072
566
tokens/s
18.5
tokens/s
2.31
sec
pp384+tg1152
583
tokens/s
20.1
tokens/s
703
ms
pp64+tg1024
516
tokens/s
20.3
tokens/s
185
ms
pp16+tg1536
200
tokens/s
20.1
tokens/s
122
ms