TEST #4139 RESULTS
09/09/2026 - 4:40 PM
ACCELERATOR
MODEL
11.3
tokens/s
generation
609
ms
time to first token
2144
tokens/s
prompt
341
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
2857
tokens/s
11.7
tokens/s
444
ms
pp4096+tg256
2678
tokens/s
11.0
tokens/s
1.62
sec
pp2048+tg256
2783
tokens/s
11.2
tokens/s
824
ms
pp2048+tg768
2746
tokens/s
11.1
tokens/s
836
ms
pp1024+tg1024
2823
tokens/s
11.2
tokens/s
451
ms
pp1280+tg3072
2478
tokens/s
11.1
tokens/s
609
ms
pp384+tg1152
2341
tokens/s
11.5
tokens/s
253
ms
pp64+tg1024
473
tokens/s
11.4
tokens/s
222
ms
pp16+tg1536
120
tokens/s
11.3
tokens/s
220
ms