TEST #153 RESULTS
03/28/2025 - 10:30 PM
ACCELERATOR
MODEL
42.6
tokens/s
generation
752
ms
time to first token
1752
tokens/s
prompt
463
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 v2 @ 3.00GHz (ivybridge)
RAM
62.8GB
OS
Linux
Kernel Release
5.15.0-131-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #141~20.04.1-Ubuntu SMP Thu Jan 16 18:38:51 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2079
tokens/s
43.8
tokens/s
516
ms
pp4096+tg256
1640
tokens/s
39.1
tokens/s
2.52
sec
pp2048+tg256
1898
tokens/s
42.1
tokens/s
1.10
sec
pp2048+tg768
1895
tokens/s
41.7
tokens/s
1.10
sec
pp1024+tg1024
2065
tokens/s
43.1
tokens/s
519
ms
pp1280+tg3072
2014
tokens/s
41.1
tokens/s
659
ms
pp384+tg1152
2219
tokens/s
44.0
tokens/s
196
ms
pp64+tg1024
1572
tokens/s
44.5
tokens/s
80
ms
pp16+tg1536
387
tokens/s
44.2
tokens/s
63
ms