TEST #1121 RESULTS
06/25/2025 - 8:33 PM
ACCELERATOR
MODEL
41.2
tokens/s
generation
143
ms
time to first token
9533
tokens/s
prompt
1400
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
12690
tokens/s
40.9
tokens/s
106
ms
pp4096+tg256
11125
tokens/s
40.4
tokens/s
393
ms
pp2048+tg256
12178
tokens/s
41.2
tokens/s
194
ms
pp2048+tg768
12415
tokens/s
41.0
tokens/s
189
ms
pp1024+tg1024
13209
tokens/s
40.9
tokens/s
102
ms
pp1280+tg3072
11422
tokens/s
40.6
tokens/s
137
ms
pp384+tg1152
10382
tokens/s
41.8
tokens/s
63
ms
pp64+tg1024
1882
tokens/s
42.0
tokens/s
54
ms
pp16+tg1536
490
tokens/s
41.9
tokens/s
53
ms