TEST #2276 RESULTS
01/13/2026 - 12:23 PM
ACCELERATOR
MODEL
4.0
tokens/s
generation
57.39
sec
time to first token
24
tokens/s
prompt
12
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
63.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
25
tokens/s
4.0
tokens/s
40.84
sec
pp4096+tg256
22
tokens/s
3.5
tokens/s
185.89
sec
pp2048+tg256
23
tokens/s
3.9
tokens/s
87.58
sec
pp2048+tg768
24
tokens/s
3.7
tokens/s
85.76
sec
pp1024+tg1024
27
tokens/s
4.2
tokens/s
38.54
sec
pp1280+tg3072
21
tokens/s
3.9
tokens/s
59.92
sec
pp384+tg1152
28
tokens/s
4.1
tokens/s
13.96
sec
pp64+tg1024
22
tokens/s
4.2
tokens/s
3.09
sec
pp16+tg1536
22
tokens/s
4.3
tokens/s
967
ms