TEST #1769 RESULTS
11/09/2025 - 10:03 AM
ACCELERATOR
MODEL
57.4
tokens/s
generation
450
ms
time to first token
2938
tokens/s
prompt
721
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.1.0-40-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.153-1 (2025-09-20)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3592
tokens/s
58.7
tokens/s
302
ms
pp4096+tg256
2685
tokens/s
52.9
tokens/s
1.55
sec
pp2048+tg256
3231
tokens/s
56.8
tokens/s
651
ms
pp2048+tg768
3228
tokens/s
56.2
tokens/s
652
ms
pp1024+tg1024
3599
tokens/s
57.9
tokens/s
301
ms
pp1280+tg3072
3493
tokens/s
55.3
tokens/s
383
ms
pp384+tg1152
3822
tokens/s
59.1
tokens/s
128
ms
pp64+tg1024
2154
tokens/s
59.8
tokens/s
46
ms
pp16+tg1536
632
tokens/s
59.4
tokens/s
42
ms