TEST #817 RESULTS
05/04/2025 - 12:08 PM
ACCELERATOR
MODEL
169
tokens/s
generation
227
ms
time to first token
6019
tokens/s
prompt
1650
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
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
7721
tokens/s
138
tokens/s
141
ms
pp4096+tg256
4971
tokens/s
142
tokens/s
831
ms
pp2048+tg256
6537
tokens/s
154
tokens/s
320
ms
pp2048+tg768
6506
tokens/s
171
tokens/s
321
ms
pp1024+tg1024
7602
tokens/s
186
tokens/s
141
ms
pp1280+tg3072
7202
tokens/s
168
tokens/s
187
ms
pp384+tg1152
8555
tokens/s
185
tokens/s
50
ms
pp64+tg1024
4410
tokens/s
188
tokens/s
20
ms
pp16+tg1536
669
tokens/s
188
tokens/s
29
ms