TEST #2156 RESULTS
01/06/2026 - 1:04 AM
ACCELERATOR
MODEL
18.8
tokens/s
generation
1.20
sec
time to first token
1145
tokens/s
prompt
262
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.6GB
OS
Linux
Kernel Release
6.14.0-1015-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #15-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 25 18:02:16 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1434
tokens/s
19.2
tokens/s
767
ms
pp4096+tg256
999
tokens/s
17.2
tokens/s
4.16
sec
pp2048+tg256
1252
tokens/s
18.2
tokens/s
1.69
sec
pp2048+tg768
1165
tokens/s
18.5
tokens/s
1.81
sec
pp1024+tg1024
1412
tokens/s
19.1
tokens/s
778
ms
pp1280+tg3072
1374
tokens/s
18.0
tokens/s
988
ms
pp384+tg1152
1566
tokens/s
19.5
tokens/s
299
ms
pp64+tg1024
842
tokens/s
19.9
tokens/s
156
ms
pp16+tg1536
260
tokens/s
19.5
tokens/s
113
ms