TEST #448 RESULTS
04/07/2025 - 12:21 AM
ACCELERATOR
MODEL
26.8
tokens/s
generation
1.07
sec
time to first token
1260
tokens/s
prompt
316
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 4600G with Radeon Graphics (znver2)
RAM
94.1GB
OS
Linux
Kernel Release
6.12.21-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.21-1 (2025-03-30)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1513
tokens/s
27.6
tokens/s
714
ms
pp4096+tg256
1119
tokens/s
24.5
tokens/s
3.70
sec
pp2048+tg256
1331
tokens/s
26.4
tokens/s
1.58
sec
pp2048+tg768
1356
tokens/s
26.2
tokens/s
1.55
sec
pp1024+tg1024
1513
tokens/s
27.0
tokens/s
713
ms
pp1280+tg3072
1458
tokens/s
25.8
tokens/s
915
ms
pp384+tg1152
1666
tokens/s
27.7
tokens/s
266
ms
pp64+tg1024
1041
tokens/s
28.1
tokens/s
114
ms
pp16+tg1536
339
tokens/s
27.9
tokens/s
82
ms