TEST #1798 RESULTS
11/14/2025 - 11:31 AM
ACCELERATOR
MODEL
3.5
tokens/s
generation
5.74
sec
time to first token
343
tokens/s
prompt
59
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6426Y (sapphirerapids)
RAM
64GB
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
205
tokens/s
3.2
tokens/s
5.31
sec
pp4096+tg256
137
tokens/s
2.5
tokens/s
30.39
sec
pp2048+tg256
530
tokens/s
3.6
tokens/s
4.14
sec
pp2048+tg768
512
tokens/s
3.6
tokens/s
4.28
sec
pp1024+tg1024
519
tokens/s
3.6
tokens/s
2.25
sec
pp1280+tg3072
479
tokens/s
3.3
tokens/s
2.96
sec
pp384+tg1152
469
tokens/s
3.7
tokens/s
1.11
sec
pp64+tg1024
190
tokens/s
3.8
tokens/s
600
ms
pp16+tg1536
49
tokens/s
3.8
tokens/s
594
ms