TEST #2781 RESULTS
02/22/2026 - 11:51 AM
ACCELERATOR
MODEL
123
tokens/s
generation
90
ms
time to first token
14483
tokens/s
prompt
2703
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
19693
tokens/s
144
tokens/s
59
ms
pp4096+tg256
14750
tokens/s
96.3
tokens/s
288
ms
pp2048+tg256
17377
tokens/s
124
tokens/s
126
ms
pp2048+tg768
17317
tokens/s
106
tokens/s
127
ms
pp1024+tg1024
19795
tokens/s
125
tokens/s
59
ms
pp1280+tg3072
17625
tokens/s
109
tokens/s
81
ms
pp384+tg1152
18273
tokens/s
132
tokens/s
29
ms
pp64+tg1024
4316
tokens/s
135
tokens/s
22
ms
pp16+tg1536
1198
tokens/s
135
tokens/s
20
ms