TEST #2774 RESULTS
02/21/2026 - 7:50 PM
ACCELERATOR
MODEL
23.2
tokens/s
generation
889
ms
time to first token
1482
tokens/s
prompt
338
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
1407
tokens/s
23.4
tokens/s
767
ms
pp4096+tg256
1317
tokens/s
15.4
tokens/s
3.17
sec
pp2048+tg256
1790
tokens/s
21.9
tokens/s
1.19
sec
pp2048+tg768
1825
tokens/s
20.5
tokens/s
1.17
sec
pp1024+tg1024
2162
tokens/s
25.2
tokens/s
514
ms
pp1280+tg3072
1822
tokens/s
18.8
tokens/s
744
ms
pp384+tg1152
1799
tokens/s
27.1
tokens/s
249
ms
pp64+tg1024
912
tokens/s
28.8
tokens/s
102
ms
pp16+tg1536
302
tokens/s
27.8
tokens/s
85
ms