TEST #3064 RESULTS
03/12/2026 - 1:08 AM
ACCELERATOR
MODEL
29.5
tokens/s
generation
1.62
sec
time to first token
802
tokens/s
prompt
244
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-14700 (alderlake)
RAM
93.9GB
OS
Linux
Kernel Release
6.12.73+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.73-1 (2026-02-17)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
937
tokens/s
31.0
tokens/s
1.13
sec
pp4096+tg256
766
tokens/s
25.9
tokens/s
5.39
sec
pp2048+tg256
858
tokens/s
28.8
tokens/s
2.42
sec
pp2048+tg768
858
tokens/s
28.4
tokens/s
2.42
sec
pp1024+tg1024
920
tokens/s
29.8
tokens/s
1.15
sec
pp1280+tg3072
892
tokens/s
27.7
tokens/s
1.47
sec
pp384+tg1152
942
tokens/s
30.9
tokens/s
439
ms
pp64+tg1024
723
tokens/s
31.7
tokens/s
124
ms
pp16+tg1536
322
tokens/s
31.3
tokens/s
80
ms