TEST #2272 RESULTS
01/13/2026 - 2:51 AM
ACCELERATOR
MODEL
24.5
tokens/s
generation
1.26
sec
time to first token
1066
tokens/s
prompt
274
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2133 CPU @ 3.60GHz (skylake-avx512)
RAM
94.3GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1257
tokens/s
25.3
tokens/s
855
ms
pp4096+tg256
964
tokens/s
22.7
tokens/s
4.29
sec
pp2048+tg256
1135
tokens/s
24.3
tokens/s
1.85
sec
pp2048+tg768
1130
tokens/s
24.1
tokens/s
1.85
sec
pp1024+tg1024
1238
tokens/s
24.8
tokens/s
867
ms
pp1280+tg3072
1194
tokens/s
23.6
tokens/s
1.11
sec
pp384+tg1152
1340
tokens/s
25.2
tokens/s
326
ms
pp64+tg1024
1074
tokens/s
25.5
tokens/s
127
ms
pp16+tg1536
259
tokens/s
25.3
tokens/s
100
ms