TEST #2906 RESULTS
02/26/2026 - 12:21 PM
ACCELERATOR
MODEL
23.1
tokens/s
generation
837
ms
time to first token
2118
tokens/s
prompt
388
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
3.8GB
OS
Linux
Kernel Release
6.17.0-14-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #14~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jan 15 15:52:10 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2576
tokens/s
25.1
tokens/s
437
ms
pp4096+tg256
2126
tokens/s
14.8
tokens/s
2.00
sec
pp2048+tg256
2572
tokens/s
20.8
tokens/s
845
ms
pp2048+tg768
2638
tokens/s
20.5
tokens/s
825
ms
pp1024+tg1024
2990
tokens/s
23.7
tokens/s
383
ms
pp1280+tg3072
2648
tokens/s
18.9
tokens/s
525
ms
pp384+tg1152
2866
tokens/s
27.0
tokens/s
170
ms
pp64+tg1024
639
tokens/s
29.4
tokens/s
136
ms
pp16+tg1536
7
tokens/s
27.9
tokens/s
2.21
sec