TEST #1130 RESULTS
06/26/2025 - 9:19 PM
ACCELERATOR
MODEL
41.4
tokens/s
generation
136
ms
time to first token
10144
tokens/s
prompt
1457
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
63.6GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10854
tokens/s
43.1
tokens/s
117
ms
pp4096+tg256
12586
tokens/s
41.0
tokens/s
350
ms
pp2048+tg256
13524
tokens/s
40.5
tokens/s
176
ms
pp2048+tg768
13243
tokens/s
40.2
tokens/s
180
ms
pp1024+tg1024
14634
tokens/s
40.7
tokens/s
95
ms
pp1280+tg3072
12834
tokens/s
40.6
tokens/s
124
ms
pp384+tg1152
11378
tokens/s
41.7
tokens/s
67
ms
pp64+tg1024
1768
tokens/s
42.3
tokens/s
57
ms
pp16+tg1536
475
tokens/s
41.9
tokens/s
54
ms