TEST #3047 RESULTS
03/08/2026 - 1:57 PM
ACCELERATOR
MODEL
51.4
tokens/s
generation
976
ms
time to first token
1197
tokens/s
prompt
398
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
31.2GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1572
tokens/s
54.7
tokens/s
670
ms
pp4096+tg256
1331
tokens/s
42.3
tokens/s
3.10
sec
pp2048+tg256
1478
tokens/s
49.8
tokens/s
1.41
sec
pp2048+tg768
1481
tokens/s
48.5
tokens/s
1.40
sec
pp1024+tg1024
1562
tokens/s
52.8
tokens/s
674
ms
pp1280+tg3072
1406
tokens/s
46.8
tokens/s
929
ms
pp384+tg1152
1300
tokens/s
55.1
tokens/s
313
ms
pp64+tg1024
351
tokens/s
56.8
tokens/s
216
ms
pp16+tg1536
290
tokens/s
55.7
tokens/s
72
ms