TEST #1919 RESULTS
12/08/2025 - 1:35 PM
ACCELERATOR
MODEL
27.1
tokens/s
generation
772
ms
time to first token
1692
tokens/s
prompt
390
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9375F 32-Core Processor
RAM
314.3GB
OS
Linux
Kernel Release
6.14.11-3-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.14.11-3 (2025-09-22T10:13Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2211
tokens/s
30.5
tokens/s
497
ms
pp4096+tg256
1563
tokens/s
21.8
tokens/s
2.67
sec
pp2048+tg256
1901
tokens/s
26.0
tokens/s
1.12
sec
pp2048+tg768
1910
tokens/s
25.3
tokens/s
1.11
sec
pp1024+tg1024
2197
tokens/s
27.7
tokens/s
500
ms
pp1280+tg3072
2077
tokens/s
24.2
tokens/s
652
ms
pp384+tg1152
2137
tokens/s
29.2
tokens/s
216
ms
pp64+tg1024
910
tokens/s
30.1
tokens/s
100
ms
pp16+tg1536
322
tokens/s
29.5
tokens/s
82
ms