TEST #2301 RESULTS
01/15/2026 - 2:26 PM
ACCELERATOR
MODEL
22.6
tokens/s
generation
1.03
sec
time to first token
1284
tokens/s
prompt
304
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
7.7GB
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
1403
tokens/s
20.9
tokens/s
764
ms
pp4096+tg256
1171
tokens/s
22.5
tokens/s
3.54
sec
pp2048+tg256
1492
tokens/s
22.8
tokens/s
1.41
sec
pp2048+tg768
1382
tokens/s
25.5
tokens/s
1.52
sec
pp1024+tg1024
1627
tokens/s
22.2
tokens/s
666
ms
pp1280+tg3072
1466
tokens/s
22.5
tokens/s
912
ms
pp384+tg1152
1643
tokens/s
25.6
tokens/s
269
ms
pp64+tg1024
1019
tokens/s
16.5
tokens/s
147
ms
pp16+tg1536
352
tokens/s
24.5
tokens/s
85
ms