TEST #1492 RESULTS
09/08/2025 - 7:39 PM
ACCELERATOR
MODEL
45.1
tokens/s
generation
127
ms
time to first token
10856
tokens/s
prompt
1567
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
15210
tokens/s
45.7
tokens/s
89
ms
pp4096+tg256
13496
tokens/s
44.6
tokens/s
326
ms
pp2048+tg256
14676
tokens/s
44.8
tokens/s
161
ms
pp2048+tg768
14089
tokens/s
44.6
tokens/s
168
ms
pp1024+tg1024
12924
tokens/s
44.6
tokens/s
125
ms
pp1280+tg3072
13185
tokens/s
44.5
tokens/s
120
ms
pp384+tg1152
11684
tokens/s
44.8
tokens/s
55
ms
pp64+tg1024
1940
tokens/s
46.4
tokens/s
52
ms
pp16+tg1536
503
tokens/s
45.9
tokens/s
50
ms