TEST #763 RESULTS
04/24/2025 - 11:02 PM
ACCELERATOR
MODEL
185
tokens/s
generation
116
ms
time to first token
11628
tokens/s
prompt
2641
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800X 8-Core Processor (znver3)
RAM
63.9GB
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
14845
tokens/s
178
tokens/s
75
ms
pp4096+tg256
9953
tokens/s
178
tokens/s
418
ms
pp2048+tg256
13113
tokens/s
189
tokens/s
162
ms
pp2048+tg768
13110
tokens/s
190
tokens/s
162
ms
pp1024+tg1024
15151
tokens/s
189
tokens/s
73
ms
pp1280+tg3072
14374
tokens/s
189
tokens/s
96
ms
pp384+tg1152
15867
tokens/s
184
tokens/s
30
ms
pp64+tg1024
7018
tokens/s
180
tokens/s
15
ms
pp16+tg1536
1222
tokens/s
185
tokens/s
19
ms