TEST #1013 RESULTS
06/07/2025 - 1:37 AM
ACCELERATOR
MODEL
43.4
tokens/s
generation
134
ms
time to first token
10569
tokens/s
prompt
1509
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
63.6GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
14093
tokens/s
44.4
tokens/s
95
ms
pp4096+tg256
12013
tokens/s
41.0
tokens/s
364
ms
pp2048+tg256
12695
tokens/s
41.1
tokens/s
190
ms
pp2048+tg768
14047
tokens/s
41.9
tokens/s
168
ms
pp1024+tg1024
15571
tokens/s
42.8
tokens/s
89
ms
pp1280+tg3072
12471
tokens/s
42.5
tokens/s
127
ms
pp384+tg1152
11794
tokens/s
45.7
tokens/s
57
ms
pp64+tg1024
1997
tokens/s
45.7
tokens/s
52
ms
pp16+tg1536
436
tokens/s
45.7
tokens/s
61
ms