TEST #91 RESULTS
03/28/2025 - 9:24 PM
ACCELERATOR
MODEL
31.9
tokens/s
generation
429
ms
time to first token
3161
tokens/s
prompt
617
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7950X 16-Core Processor (znver4)
RAM
125GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4280
tokens/s
35.7
tokens/s
267
ms
pp4096+tg256
2820
tokens/s
25.3
tokens/s
1.49
sec
pp2048+tg256
3567
tokens/s
31.7
tokens/s
606
ms
pp2048+tg768
3563
tokens/s
28.6
tokens/s
606
ms
pp1024+tg1024
4283
tokens/s
32.9
tokens/s
268
ms
pp1280+tg3072
3931
tokens/s
28.0
tokens/s
355
ms
pp384+tg1152
4224
tokens/s
34.4
tokens/s
121
ms
pp64+tg1024
1378
tokens/s
35.4
tokens/s
75
ms
pp16+tg1536
398
tokens/s
34.8
tokens/s
68
ms