TEST #2783 RESULTS
02/22/2026 - 4:21 PM
ACCELERATOR
MODEL
4.9
tokens/s
generation
62.02
sec
time to first token
22
tokens/s
prompt
12
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 6900HX with Radeon Graphics (znver3)
RAM
27.2GB
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
16
tokens/s
5.3
tokens/s
62.43
sec
pp4096+tg256
20
tokens/s
4.0
tokens/s
200.79
sec
pp2048+tg256
21
tokens/s
4.9
tokens/s
97.10
sec
pp2048+tg768
24
tokens/s
4.7
tokens/s
86.05
sec
pp1024+tg1024
25
tokens/s
5.1
tokens/s
40.48
sec
pp1280+tg3072
25
tokens/s
4.6
tokens/s
52.31
sec
pp384+tg1152
26
tokens/s
5.1
tokens/s
15.12
sec
pp64+tg1024
25
tokens/s
5.2
tokens/s
2.76
sec
pp16+tg1536
17
tokens/s
5.2
tokens/s
1.16
sec