TEST #3598 RESULTS
05/22/2026 - 2:33 PM
ACCELERATOR
MODEL
40.3
tokens/s
generation
548
ms
time to first token
2367
tokens/s
prompt
559
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2963
tokens/s
40.3
tokens/s
371
ms
pp4096+tg256
2299
tokens/s
39.6
tokens/s
1.81
sec
pp2048+tg256
2585
tokens/s
39.2
tokens/s
818
ms
pp2048+tg768
2662
tokens/s
39.8
tokens/s
796
ms
pp1024+tg1024
2969
tokens/s
40.4
tokens/s
370
ms
pp1280+tg3072
2872
tokens/s
40.2
tokens/s
469
ms
pp384+tg1152
3235
tokens/s
40.7
tokens/s
159
ms
pp64+tg1024
1248
tokens/s
41.4
tokens/s
80
ms
pp16+tg1536
476
tokens/s
41.4
tokens/s
61
ms