TEST #671 RESULTS
04/10/2025 - 3:09 PM
ACCELERATOR
MODEL
202
tokens/s
generation
149
ms
time to first token
8883
tokens/s
prompt
2294
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
95.9GB
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
11477
tokens/s
208
tokens/s
94
ms
pp4096+tg256
7757
tokens/s
168
tokens/s
535
ms
pp2048+tg256
10002
tokens/s
201
tokens/s
210
ms
pp2048+tg768
9991
tokens/s
197
tokens/s
210
ms
pp1024+tg1024
11560
tokens/s
210
tokens/s
94
ms
pp1280+tg3072
10691
tokens/s
190
tokens/s
125
ms
pp384+tg1152
10966
tokens/s
215
tokens/s
40
ms
pp64+tg1024
6077
tokens/s
215
tokens/s
16
ms
pp16+tg1536
1428
tokens/s
214
tokens/s
16
ms