TEST #949 RESULTS
05/27/2025 - 7:13 PM
ACCELERATOR
MODEL
15.7
tokens/s
generation
4.94
sec
time to first token
316
tokens/s
prompt
100
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.14.6-300.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri May 9 20:11:19 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
356
tokens/s
20.1
tokens/s
2.93
sec
pp4096+tg256
211
tokens/s
2.3
tokens/s
19.87
sec
pp2048+tg256
304
tokens/s
14.8
tokens/s
6.80
sec
pp2048+tg768
304
tokens/s
13.9
tokens/s
6.79
sec
pp1024+tg1024
356
tokens/s
17.0
tokens/s
2.92
sec
pp1280+tg3072
345
tokens/s
8.9
tokens/s
3.76
sec
pp384+tg1152
397
tokens/s
20.1
tokens/s
1.01
sec
pp64+tg1024
347
tokens/s
22.7
tokens/s
222
ms
pp16+tg1536
227
tokens/s
21.6
tokens/s
107
ms