TEST #1562 RESULTS
09/26/2025 - 12:03 PM
ACCELERATOR
MODEL
49.5
tokens/s
generation
631
ms
time to first token
4295
tokens/s
prompt
696
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.8GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3759
tokens/s
54.0
tokens/s
293
ms
pp4096+tg256
4304
tokens/s
39.3
tokens/s
976
ms
pp2048+tg256
5451
tokens/s
47.3
tokens/s
395
ms
pp2048+tg768
5548
tokens/s
45.8
tokens/s
389
ms
pp1024+tg1024
6094
tokens/s
50.9
tokens/s
186
ms
pp1280+tg3072
5734
tokens/s
44.4
tokens/s
242
ms
pp384+tg1152
5816
tokens/s
53.9
tokens/s
84
ms
pp64+tg1024
1947
tokens/s
55.6
tokens/s
50
ms
pp16+tg1536
5
tokens/s
54.7
tokens/s
3.06
sec