TEST #3524 RESULTS
05/13/2026 - 6:13 PM
ACCELERATOR
MODEL
37.1
tokens/s
generation
1.18
sec
time to first token
1077
tokens/s
prompt
323
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7251 8-Core Processor
RAM
220.3GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1196
tokens/s
38.4
tokens/s
882
ms
pp4096+tg256
1058
tokens/s
31.0
tokens/s
3.90
sec
pp2048+tg256
1200
tokens/s
35.8
tokens/s
1.73
sec
pp2048+tg768
1202
tokens/s
35.2
tokens/s
1.73
sec
pp1024+tg1024
1273
tokens/s
37.8
tokens/s
830
ms
pp1280+tg3072
1243
tokens/s
34.4
tokens/s
1.06
sec
pp384+tg1152
1279
tokens/s
39.7
tokens/s
324
ms
pp64+tg1024
991
tokens/s
41.0
tokens/s
88
ms
pp16+tg1536
250
tokens/s
40.3
tokens/s
87
ms