TEST #443 RESULTS
04/06/2025 - 11:42 PM
ACCELERATOR
MODEL
199
tokens/s
generation
104
ms
time to first token
14206
tokens/s
prompt
3006
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.7GB
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
19042
tokens/s
229
tokens/s
58
ms
pp4096+tg256
10322
tokens/s
220
tokens/s
401
ms
pp2048+tg256
15061
tokens/s
191
tokens/s
141
ms
pp2048+tg768
14769
tokens/s
192
tokens/s
153
ms
pp1024+tg1024
19631
tokens/s
194
tokens/s
58
ms
pp1280+tg3072
18808
tokens/s
191
tokens/s
72
ms
pp384+tg1152
24021
tokens/s
187
tokens/s
22
ms
pp64+tg1024
3872
tokens/s
193
tokens/s
21
ms
pp16+tg1536
2327
tokens/s
193
tokens/s
11
ms