TEST #1810 RESULTS
11/16/2025 - 10:51 AM
ACCELERATOR
MODEL
216
tokens/s
generation
223
ms
time to first token
8295
tokens/s
prompt
2002
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
31.9GB
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
10634
tokens/s
221
tokens/s
102
ms
pp4096+tg256
6660
tokens/s
195
tokens/s
620
ms
pp2048+tg256
8902
tokens/s
215
tokens/s
235
ms
pp2048+tg768
8862
tokens/s
211
tokens/s
236
ms
pp1024+tg1024
10657
tokens/s
221
tokens/s
101
ms
pp1280+tg3072
9901
tokens/s
207
tokens/s
134
ms
pp384+tg1152
11948
tokens/s
224
tokens/s
37
ms
pp64+tg1024
7060
tokens/s
225
tokens/s
13
ms
pp16+tg1536
30
tokens/s
226
tokens/s
531
ms