TEST #177 RESULTS
03/30/2025 - 8:19 PM
ACCELERATOR
MODEL
65.3
tokens/s
generation
281
ms
time to first token
4777
tokens/s
prompt
1036
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
125.7GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6208
tokens/s
73.2
tokens/s
179
ms
pp4096+tg256
4415
tokens/s
46.2
tokens/s
949
ms
pp2048+tg256
5477
tokens/s
61.4
tokens/s
390
ms
pp2048+tg768
5466
tokens/s
58.1
tokens/s
391
ms
pp1024+tg1024
6220
tokens/s
66.4
tokens/s
179
ms
pp1280+tg3072
5834
tokens/s
54.9
tokens/s
234
ms
pp384+tg1152
6329
tokens/s
73.4
tokens/s
73
ms
pp64+tg1024
2853
tokens/s
78.3
tokens/s
34
ms
pp16+tg1536
188
tokens/s
75.7
tokens/s
96
ms