TEST #467 RESULTS
04/07/2025 - 4:03 AM
ACCELERATOR
MODEL
218
tokens/s
generation
167
ms
time to first token
8237
tokens/s
prompt
2205
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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10374
tokens/s
224
tokens/s
103
ms
pp4096+tg256
6626
tokens/s
191
tokens/s
624
ms
pp2048+tg256
8807
tokens/s
214
tokens/s
237
ms
pp2048+tg768
8788
tokens/s
212
tokens/s
238
ms
pp1024+tg1024
10526
tokens/s
222
tokens/s
103
ms
pp1280+tg3072
9950
tokens/s
206
tokens/s
133
ms
pp384+tg1152
11488
tokens/s
228
tokens/s
38
ms
pp64+tg1024
6157
tokens/s
233
tokens/s
14
ms
pp16+tg1536
1418
tokens/s
230
tokens/s
15
ms