TEST #970 RESULTS
06/02/2025 - 4:08 AM
ACCELERATOR
MODEL
70.5
tokens/s
generation
336
ms
time to first token
3905
tokens/s
prompt
935
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 5218 CPU @ 2.30GHz (cascadelake)
RAM
503.7GB
OS
Linux
Kernel Release
6.8.0-58-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #60-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 14 18:29:48 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4865
tokens/s
72.6
tokens/s
225
ms
pp4096+tg256
3735
tokens/s
64.3
tokens/s
1.11
sec
pp2048+tg256
4424
tokens/s
69.6
tokens/s
478
ms
pp2048+tg768
4419
tokens/s
68.9
tokens/s
478
ms
pp1024+tg1024
4876
tokens/s
71.1
tokens/s
224
ms
pp1280+tg3072
4696
tokens/s
67.9
tokens/s
287
ms
pp384+tg1152
5087
tokens/s
72.5
tokens/s
148
ms
pp64+tg1024
2230
tokens/s
74.0
tokens/s
42
ms
pp16+tg1536
813
tokens/s
73.3
tokens/s
33
ms