TEST #1730 RESULTS
11/04/2025 - 7:40 AM
ACCELERATOR
MODEL
23.9
tokens/s
generation
3.80
sec
time to first token
373
tokens/s
prompt
133
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 9995WX
RAM
498.8GB
OS
Linux
Kernel Release
6.14.0-34-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #34-Ubuntu SMP PREEMPT_DYNAMIC Wed Sep 17 09:21:29 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
415
tokens/s
24.2
tokens/s
2.51
sec
pp4096+tg256
313
tokens/s
21.8
tokens/s
13.13
sec
pp2048+tg256
361
tokens/s
23.6
tokens/s
5.72
sec
pp2048+tg768
369
tokens/s
23.4
tokens/s
5.59
sec
pp1024+tg1024
366
tokens/s
24.2
tokens/s
2.84
sec
pp1280+tg3072
404
tokens/s
23.2
tokens/s
3.21
sec
pp384+tg1152
454
tokens/s
24.5
tokens/s
885
ms
pp64+tg1024
428
tokens/s
25.0
tokens/s
189
ms
pp16+tg1536
249
tokens/s
24.8
tokens/s
105
ms