TEST #375 RESULTS
04/06/2025 - 2:08 PM
ACCELERATOR
MODEL
185
tokens/s
generation
157
ms
time to first token
8285
tokens/s
prompt
2137
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-7700K CPU @ 4.20GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
5.15.167.4-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Tue Nov 5 00:21:55 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11070
tokens/s
186
tokens/s
98
ms
pp4096+tg256
7632
tokens/s
149
tokens/s
544
ms
pp2048+tg256
9769
tokens/s
180
tokens/s
215
ms
pp2048+tg768
9600
tokens/s
177
tokens/s
222
ms
pp1024+tg1024
10148
tokens/s
191
tokens/s
106
ms
pp1280+tg3072
10229
tokens/s
168
tokens/s
134
ms
pp384+tg1152
9782
tokens/s
200
tokens/s
45
ms
pp64+tg1024
5699
tokens/s
208
tokens/s
16
ms
pp16+tg1536
638
tokens/s
201
tokens/s
30
ms