TEST #1760 RESULTS
11/08/2025 - 4:08 PM
ACCELERATOR
MODEL
30.5
tokens/s
generation
1.67
sec
time to first token
1161
tokens/s
prompt
277
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
93GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
790
tokens/s
32.2
tokens/s
1.33
sec
pp4096+tg256
1043
tokens/s
23.8
tokens/s
3.97
sec
pp2048+tg256
1334
tokens/s
29.0
tokens/s
1.57
sec
pp2048+tg768
1349
tokens/s
28.2
tokens/s
1.55
sec
pp1024+tg1024
1530
tokens/s
31.2
tokens/s
699
ms
pp1280+tg3072
1466
tokens/s
27.2
tokens/s
905
ms
pp384+tg1152
1743
tokens/s
33.5
tokens/s
248
ms
pp64+tg1024
1193
tokens/s
35.2
tokens/s
80
ms
pp16+tg1536
3
tokens/s
34.4
tokens/s
4.65
sec