TEST #679 RESULTS
04/10/2025 - 7:18 PM
ACCELERATOR
MODEL
37.9
tokens/s
generation
994
ms
time to first token
1254
tokens/s
prompt
363
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 14B Instruct AWQ - Q4_0
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
95.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1563
tokens/s
42.1
tokens/s
680
ms
pp4096+tg256
1273
tokens/s
29.7
tokens/s
3.25
sec
pp2048+tg256
1445
tokens/s
37.8
tokens/s
1.44
sec
pp2048+tg768
1447
tokens/s
37.2
tokens/s
1.44
sec
pp1024+tg1024
1466
tokens/s
38.7
tokens/s
723
ms
pp1280+tg3072
1409
tokens/s
34.6
tokens/s
936
ms
pp384+tg1152
1337
tokens/s
40.0
tokens/s
313
ms
pp64+tg1024
997
tokens/s
40.6
tokens/s
89
ms
pp16+tg1536
349
tokens/s
40.2
tokens/s
70
ms