TEST #473 RESULTS
04/07/2025 - 4:49 AM
ACCELERATOR
MODEL
202
tokens/s
generation
236
ms
time to first token
5800
tokens/s
prompt
1706
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
62.7GB
OS
Linux
Kernel Release
6.13.8-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun, 23 Mar 2025 17:17:30 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7368
tokens/s
221
tokens/s
143
ms
pp4096+tg256
4703
tokens/s
162
tokens/s
878
ms
pp2048+tg256
6235
tokens/s
195
tokens/s
333
ms
pp2048+tg768
6167
tokens/s
188
tokens/s
338
ms
pp1024+tg1024
7315
tokens/s
206
tokens/s
144
ms
pp1280+tg3072
6974
tokens/s
179
tokens/s
188
ms
pp384+tg1152
7545
tokens/s
217
tokens/s
55
ms
pp64+tg1024
5089
tokens/s
228
tokens/s
17
ms
pp16+tg1536
801
tokens/s
221
tokens/s
24
ms