TEST #1120 RESULTS
06/25/2025 - 8:10 PM
ACCELERATOR
MODEL
41.7
tokens/s
generation
144
ms
time to first token
9611
tokens/s
prompt
1406
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
12696
tokens/s
42.4
tokens/s
103
ms
pp4096+tg256
10985
tokens/s
41.1
tokens/s
397
ms
pp2048+tg256
12544
tokens/s
41.5
tokens/s
205
ms
pp2048+tg768
12429
tokens/s
41.6
tokens/s
189
ms
pp1024+tg1024
12852
tokens/s
41.7
tokens/s
104
ms
pp1280+tg3072
11751
tokens/s
41.2
tokens/s
133
ms
pp384+tg1152
10976
tokens/s
42.0
tokens/s
59
ms
pp64+tg1024
1786
tokens/s
42.0
tokens/s
56
ms
pp16+tg1536
482
tokens/s
41.9
tokens/s
53
ms