TEST #2778 RESULTS
02/21/2026 - 11:40 PM
ACCELERATOR
MODEL
31.3
tokens/s
generation
1.35
sec
time to first token
1287
tokens/s
prompt
310
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
62.7GB
OS
Linux
Kernel Release
6.17.0-14-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #14~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jan 15 15:52:10 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1558
tokens/s
34.0
tokens/s
687
ms
pp4096+tg256
1121
tokens/s
24.1
tokens/s
3.70
sec
pp2048+tg256
1375
tokens/s
29.3
tokens/s
1.52
sec
pp2048+tg768
1374
tokens/s
28.9
tokens/s
1.52
sec
pp1024+tg1024
1559
tokens/s
32.0
tokens/s
687
ms
pp1280+tg3072
1500
tokens/s
27.8
tokens/s
884
ms
pp384+tg1152
1781
tokens/s
34.5
tokens/s
243
ms
pp64+tg1024
1313
tokens/s
36.2
tokens/s
75
ms
pp16+tg1536
6
tokens/s
35.3
tokens/s
2.85
sec