TEST #232 RESULTS
04/04/2025 - 4:20 PM
ACCELERATOR
MODEL
24.3
tokens/s
generation
754
ms
time to first token
2451
tokens/s
prompt
429
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7950X3D 16-Core Processor (znver4)
RAM
62.4GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2856
tokens/s
28.0
tokens/s
394
ms
pp4096+tg256
2452
tokens/s
16.4
tokens/s
1.73
sec
pp2048+tg256
3090
tokens/s
22.6
tokens/s
707
ms
pp2048+tg768
3074
tokens/s
21.3
tokens/s
713
ms
pp1024+tg1024
3515
tokens/s
24.3
tokens/s
329
ms
pp1280+tg3072
3064
tokens/s
19.9
tokens/s
456
ms
pp384+tg1152
3071
tokens/s
27.5
tokens/s
158
ms
pp64+tg1024
932
tokens/s
30.0
tokens/s
98
ms
pp16+tg1536
7
tokens/s
28.6
tokens/s
2.20
sec