TEST #4140 RESULTS
09/09/2026 - 6:39 PM
ACCELERATOR
MODEL
11.0
tokens/s
generation
622
ms
time to first token
2110
tokens/s
prompt
334
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 7960X 24-Cores (znver4)
RAM
94.3GB
OS
Linux
Kernel Release
6.18.40.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri Jul 31 22:12:15 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2775
tokens/s
11.1
tokens/s
458
ms
pp4096+tg256
2618
tokens/s
10.6
tokens/s
1.66
sec
pp2048+tg256
2705
tokens/s
11.0
tokens/s
855
ms
pp2048+tg768
2790
tokens/s
11.0
tokens/s
827
ms
pp1024+tg1024
2852
tokens/s
11.0
tokens/s
449
ms
pp1280+tg3072
2490
tokens/s
10.8
tokens/s
607
ms
pp384+tg1152
2213
tokens/s
11.2
tokens/s
265
ms
pp64+tg1024
440
tokens/s
10.8
tokens/s
240
ms
pp16+tg1536
110
tokens/s
11.1
tokens/s
237
ms