TEST #2786 RESULTS
02/22/2026 - 8:05 PM
ACCELERATOR
MODEL
27.6
tokens/s
generation
562
ms
time to first token
2261
tokens/s
prompt
481
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
60.3GB
OS
Linux
Kernel Release
6.17.0-14-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #14~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jan 15 15:52:10 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2906
tokens/s
33.6
tokens/s
382
ms
pp4096+tg256
2333
tokens/s
20.7
tokens/s
1.81
sec
pp2048+tg256
2665
tokens/s
26.2
tokens/s
809
ms
pp2048+tg768
2678
tokens/s
25.8
tokens/s
805
ms
pp1024+tg1024
2892
tokens/s
28.9
tokens/s
393
ms
pp1280+tg3072
2694
tokens/s
23.6
tokens/s
511
ms
pp384+tg1152
2880
tokens/s
29.6
tokens/s
168
ms
pp64+tg1024
1005
tokens/s
30.3
tokens/s
95
ms
pp16+tg1536
292
tokens/s
29.9
tokens/s
90
ms