TEST #1181 RESULTS
07/04/2025 - 8:15 PM
ACCELERATOR
MODEL
4.2
tokens/s
generation
117.37
sec
time to first token
12
tokens/s
prompt
8
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Silver 4110 CPU @ 2.10GHz (skylake-avx512)
RAM
30.8GB
OS
Linux
Kernel Release
6.1.0-37-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.140-1 (2025-05-22)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12
tokens/s
4.4
tokens/s
84.89
sec
pp4096+tg256
11
tokens/s
3.6
tokens/s
388.32
sec
pp2048+tg256
12
tokens/s
4.1
tokens/s
177.04
sec
pp2048+tg768
12
tokens/s
4.0
tokens/s
177.28
sec
pp1024+tg1024
12
tokens/s
4.2
tokens/s
84.64
sec
pp1280+tg3072
12
tokens/s
3.9
tokens/s
106.65
sec
pp384+tg1152
13
tokens/s
4.4
tokens/s
30.66
sec
pp64+tg1024
13
tokens/s
4.5
tokens/s
5.30
sec
pp16+tg1536
12
tokens/s
4.4
tokens/s
1.55
sec