TEST #1170 RESULTS
07/02/2025 - 2:30 AM
ACCELERATOR
MODEL
33.7
tokens/s
generation
945
ms
time to first token
1418
tokens/s
prompt
370
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5500 (znver3)
RAM
31.2GB
OS
Linux
Kernel Release
6.12.34-1-MANJARO
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 19 Jun 2025 15:49:06 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1663
tokens/s
35.3
tokens/s
644
ms
pp4096+tg256
1296
tokens/s
30.8
tokens/s
3.19
sec
pp2048+tg256
1511
tokens/s
33.6
tokens/s
1.39
sec
pp2048+tg768
1507
tokens/s
32.6
tokens/s
1.39
sec
pp1024+tg1024
1650
tokens/s
34.2
tokens/s
650
ms
pp1280+tg3072
1598
tokens/s
32.0
tokens/s
831
ms
pp384+tg1152
1817
tokens/s
35.0
tokens/s
239
ms
pp64+tg1024
1263
tokens/s
35.6
tokens/s
109
ms
pp16+tg1536
459
tokens/s
34.7
tokens/s
63
ms