TEST #1022 RESULTS
06/09/2025 - 7:11 AM
ACCELERATOR
MODEL
59.1
tokens/s
generation
676
ms
time to first token
1876
tokens/s
prompt
547
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3800X 8-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.11.0-26-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #26~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 17 19:20:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2250
tokens/s
62.0
tokens/s
471
ms
pp4096+tg256
1869
tokens/s
52.6
tokens/s
2.21
sec
pp2048+tg256
2090
tokens/s
58.2
tokens/s
998
ms
pp2048+tg768
2084
tokens/s
57.4
tokens/s
1.00
sec
pp1024+tg1024
2240
tokens/s
59.9
tokens/s
474
ms
pp1280+tg3072
2168
tokens/s
55.8
tokens/s
607
ms
pp384+tg1152
2261
tokens/s
61.0
tokens/s
207
ms
pp64+tg1024
1507
tokens/s
62.7
tokens/s
58
ms
pp16+tg1536
414
tokens/s
62.0
tokens/s
54
ms