TEST #1125 RESULTS
06/25/2025 - 9:10 PM
ACCELERATOR
MODEL
41.5
tokens/s
generation
135
ms
time to first token
10392
tokens/s
prompt
1474
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
13869
tokens/s
42.2
tokens/s
97
ms
pp4096+tg256
12436
tokens/s
40.7
tokens/s
355
ms
pp2048+tg256
13869
tokens/s
41.4
tokens/s
171
ms
pp2048+tg768
13405
tokens/s
41.1
tokens/s
177
ms
pp1024+tg1024
14064
tokens/s
41.2
tokens/s
96
ms
pp1280+tg3072
12829
tokens/s
40.7
tokens/s
124
ms
pp384+tg1152
11117
tokens/s
41.6
tokens/s
70
ms
pp64+tg1024
1471
tokens/s
42.4
tokens/s
64
ms
pp16+tg1536
466
tokens/s
42.2
tokens/s
56
ms