TEST #1452 RESULTS
08/29/2025 - 7:48 PM
ACCELERATOR
MODEL
181
tokens/s
generation
249
ms
time to first token
5836
tokens/s
prompt
1619
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.14.0-29-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Aug 14 16:52:50 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6758
tokens/s
197
tokens/s
157
ms
pp4096+tg256
4456
tokens/s
146
tokens/s
927
ms
pp2048+tg256
5757
tokens/s
175
tokens/s
362
ms
pp2048+tg768
5772
tokens/s
171
tokens/s
361
ms
pp1024+tg1024
6877
tokens/s
185
tokens/s
154
ms
pp1280+tg3072
6452
tokens/s
164
tokens/s
204
ms
pp384+tg1152
8652
tokens/s
195
tokens/s
49
ms
pp64+tg1024
6660
tokens/s
202
tokens/s
14
ms
pp16+tg1536
1135
tokens/s
198
tokens/s
18
ms