TEST #2772 RESULTS
02/21/2026 - 7:39 PM
ACCELERATOR
MODEL
106
tokens/s
generation
137
ms
time to first token
10130
tokens/s
prompt
1985
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
60.3GB
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
13756
tokens/s
111
tokens/s
83
ms
pp4096+tg256
9346
tokens/s
72.9
tokens/s
452
ms
pp2048+tg256
11989
tokens/s
96.3
tokens/s
181
ms
pp2048+tg768
11953
tokens/s
96.7
tokens/s
182
ms
pp1024+tg1024
13791
tokens/s
109
tokens/s
84
ms
pp1280+tg3072
12104
tokens/s
93.1
tokens/s
115
ms
pp384+tg1152
13843
tokens/s
120
tokens/s
36
ms
pp64+tg1024
4162
tokens/s
130
tokens/s
22
ms
pp16+tg1536
227
tokens/s
123
tokens/s
78
ms