TEST #2917 RESULTS
02/27/2026 - 8:20 AM
ACCELERATOR
MODEL
23.2
tokens/s
generation
580
ms
time to first token
2256
tokens/s
prompt
448
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
7.8GB
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
2954
tokens/s
25.2
tokens/s
386
ms
pp4096+tg256
2182
tokens/s
14.9
tokens/s
1.95
sec
pp2048+tg256
2670
tokens/s
20.8
tokens/s
816
ms
pp2048+tg768
2667
tokens/s
20.6
tokens/s
816
ms
pp1024+tg1024
3072
tokens/s
23.8
tokens/s
374
ms
pp1280+tg3072
2719
tokens/s
18.9
tokens/s
512
ms
pp384+tg1152
2915
tokens/s
27.1
tokens/s
168
ms
pp64+tg1024
836
tokens/s
29.3
tokens/s
112
ms
pp16+tg1536
291
tokens/s
27.9
tokens/s
88
ms