TEST #3194 RESULTS
03/25/2026 - 11:17 AM
ACCELERATOR
MODEL
16.6
tokens/s
generation
1.35
sec
time to first token
1014
tokens/s
prompt
232
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
121.6GB
OS
Linux
Kernel Release
6.17.0-1014-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #14-Ubuntu SMP PREEMPT_DYNAMIC Tue Mar 17 19:01:40 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1262
tokens/s
17.0
tokens/s
873
ms
pp4096+tg256
872
tokens/s
15.3
tokens/s
4.76
sec
pp2048+tg256
1095
tokens/s
16.4
tokens/s
1.93
sec
pp2048+tg768
1093
tokens/s
16.3
tokens/s
1.94
sec
pp1024+tg1024
1246
tokens/s
16.7
tokens/s
883
ms
pp1280+tg3072
1202
tokens/s
16.0
tokens/s
1.13
sec
pp384+tg1152
1390
tokens/s
17.2
tokens/s
337
ms
pp64+tg1024
776
tokens/s
17.4
tokens/s
180
ms
pp16+tg1536
190
tokens/s
17.3
tokens/s
139
ms