TEST #1878 RESULTS
11/28/2025 - 1:15 AM
ACCELERATOR
MODEL
15.7
tokens/s
generation
3.50
sec
time to first token
339
tokens/s
prompt
115
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2670 0 @ 2.60GHz (sandybridge)
RAM
377.8GB
OS
Linux
Kernel Release
5.15.0-161-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #171-Ubuntu SMP Sat Oct 11 08:17:01 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
464
tokens/s
19.1
tokens/s
2.26
sec
pp4096+tg256
393
tokens/s
14.5
tokens/s
10.49
sec
pp2048+tg256
435
tokens/s
18.0
tokens/s
4.76
sec
pp2048+tg768
432
tokens/s
17.2
tokens/s
4.80
sec
pp1024+tg1024
364
tokens/s
16.7
tokens/s
2.87
sec
pp1280+tg3072
292
tokens/s
13.0
tokens/s
4.45
sec
pp384+tg1152
283
tokens/s
14.4
tokens/s
1.42
sec
pp64+tg1024
257
tokens/s
14.6
tokens/s
297
ms
pp16+tg1536
132
tokens/s
14.1
tokens/s
169
ms