TEST #680 RESULTS
04/10/2025 - 7:26 PM
ACCELERATOR
MODEL
35.9
tokens/s
generation
1.10
sec
time to first token
1133
tokens/s
prompt
333
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 14B Instruct AWQ - Q4_K - Medium
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
1383
tokens/s
38.4
tokens/s
766
ms
pp4096+tg256
1148
tokens/s
28.2
tokens/s
3.60
sec
pp2048+tg256
1288
tokens/s
35.6
tokens/s
1.62
sec
pp2048+tg768
1277
tokens/s
35.1
tokens/s
1.63
sec
pp1024+tg1024
1352
tokens/s
37.1
tokens/s
785
ms
pp1280+tg3072
1295
tokens/s
33.5
tokens/s
1.01
sec
pp384+tg1152
1162
tokens/s
38.2
tokens/s
357
ms
pp64+tg1024
971
tokens/s
38.6
tokens/s
91
ms
pp16+tg1536
323
tokens/s
38.3
tokens/s
75
ms