TEST #130 RESULTS
03/28/2025 - 10:12 PM
ACCELERATOR
MODEL
29.1
tokens/s
generation
2.35
sec
time to first token
713
tokens/s
prompt
207
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
5.15.0-131-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #141~20.04.1-Ubuntu SMP Thu Jan 16 18:38:51 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
856
tokens/s
30.6
tokens/s
1.23
sec
pp4096+tg256
774
tokens/s
26.1
tokens/s
5.33
sec
pp2048+tg256
868
tokens/s
28.8
tokens/s
2.39
sec
pp2048+tg768
855
tokens/s
28.5
tokens/s
2.43
sec
pp1024+tg1024
916
tokens/s
25.8
tokens/s
1.15
sec
pp1280+tg3072
162
tokens/s
28.1
tokens/s
7.93
sec
pp384+tg1152
948
tokens/s
31.1
tokens/s
436
ms
pp64+tg1024
781
tokens/s
31.9
tokens/s
136
ms
pp16+tg1536
260
tokens/s
31.5
tokens/s
92
ms