TEST #1706 RESULTS
10/26/2025 - 7:51 PM
ACCELERATOR
MODEL
68.8
tokens/s
generation
315
ms
time to first token
4208
tokens/s
prompt
972
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 3995WX 64-Cores (znver2)
RAM
251.5GB
OS
Linux
Kernel Release
6.17.5-061705-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202510231631 SMP PREEMPT_DYNAMIC Thu Oct 23 19:57:43 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5231
tokens/s
70.2
tokens/s
211
ms
pp4096+tg256
3864
tokens/s
64.2
tokens/s
1.08
sec
pp2048+tg256
4683
tokens/s
67.9
tokens/s
452
ms
pp2048+tg768
4661
tokens/s
67.1
tokens/s
454
ms
pp1024+tg1024
5248
tokens/s
69.6
tokens/s
210
ms
pp1280+tg3072
5096
tokens/s
66.8
tokens/s
265
ms
pp384+tg1152
5497
tokens/s
70.8
tokens/s
100
ms
pp64+tg1024
2788
tokens/s
71.8
tokens/s
36
ms
pp16+tg1536
806
tokens/s
71.3
tokens/s
33
ms