TEST #3176 RESULTS
03/24/2026 - 3:40 AM
ACCELERATOR
MODEL
11.5
tokens/s
generation
4.54
sec
time to first token
245
tokens/s
prompt
85
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2135 CPU @ 3.70GHz (skylake-avx512)
RAM
125.4GB
OS
Linux
Kernel Release
6.17.13-2-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.17.13-2 (2026-03-13T08:06Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
345
tokens/s
16.8
tokens/s
3.03
sec
pp4096+tg256
304
tokens/s
12.7
tokens/s
13.56
sec
pp2048+tg256
330
tokens/s
15.8
tokens/s
6.28
sec
pp2048+tg768
327
tokens/s
15.3
tokens/s
6.32
sec
pp1024+tg1024
338
tokens/s
16.7
tokens/s
3.09
sec
pp1280+tg3072
320
tokens/s
11.1
tokens/s
4.06
sec
pp384+tg1152
141
tokens/s
5.5
tokens/s
2.87
sec
pp64+tg1024
67
tokens/s
4.7
tokens/s
1.09
sec
pp16+tg1536
38
tokens/s
4.6
tokens/s
560
ms