TEST #1119 RESULTS
06/25/2025 - 7:59 PM
ACCELERATOR
MODEL
41.1
tokens/s
generation
144
ms
time to first token
9524
tokens/s
prompt
1395
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
12419
tokens/s
41.4
tokens/s
108
ms
pp4096+tg256
11054
tokens/s
40.2
tokens/s
401
ms
pp2048+tg256
12109
tokens/s
40.2
tokens/s
191
ms
pp2048+tg768
12469
tokens/s
41.0
tokens/s
188
ms
pp1024+tg1024
12803
tokens/s
40.9
tokens/s
105
ms
pp1280+tg3072
11596
tokens/s
40.5
tokens/s
135
ms
pp384+tg1152
10957
tokens/s
41.4
tokens/s
59
ms
pp64+tg1024
1826
tokens/s
42.2
tokens/s
56
ms
pp16+tg1536
481
tokens/s
41.8
tokens/s
54
ms