TEST #1872 RESULTS
11/26/2025 - 2:54 PM
ACCELERATOR
MODEL
17.9
tokens/s
generation
1.24
sec
time to first token
1102
tokens/s
prompt
251
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.6GB
OS
Linux
Kernel Release
6.14.0-1013-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #13-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 29 06:01:19 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1356
tokens/s
18.4
tokens/s
809
ms
pp4096+tg256
948
tokens/s
16.5
tokens/s
4.38
sec
pp2048+tg256
1197
tokens/s
17.8
tokens/s
1.77
sec
pp2048+tg768
1189
tokens/s
17.6
tokens/s
1.78
sec
pp1024+tg1024
1359
tokens/s
18.0
tokens/s
813
ms
pp1280+tg3072
1292
tokens/s
17.1
tokens/s
1.05
sec
pp384+tg1152
1489
tokens/s
18.5
tokens/s
315
ms
pp64+tg1024
832
tokens/s
18.6
tokens/s
149
ms
pp16+tg1536
252
tokens/s
18.4
tokens/s
119
ms