TEST #513 RESULTS
04/07/2025 - 7:06 PM
ACCELERATOR
MODEL
29.7
tokens/s
generation
1.56
sec
time to first token
835
tokens/s
prompt
251
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2680 v4 @ 2.40GHz (broadwell)
RAM
125.8GB
OS
Linux
Kernel Release
6.1.0-31-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.128-1 (2025-02-07)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
936
tokens/s
30.9
tokens/s
1.13
sec
pp4096+tg256
795
tokens/s
26.2
tokens/s
5.19
sec
pp2048+tg256
902
tokens/s
29.1
tokens/s
2.30
sec
pp2048+tg768
903
tokens/s
28.7
tokens/s
2.30
sec
pp1024+tg1024
971
tokens/s
30.0
tokens/s
1.09
sec
pp1280+tg3072
942
tokens/s
28.1
tokens/s
1.39
sec
pp384+tg1152
1015
tokens/s
31.0
tokens/s
410
ms
pp64+tg1024
792
tokens/s
31.7
tokens/s
136
ms
pp16+tg1536
259
tokens/s
31.3
tokens/s
92
ms