TEST #2154 RESULTS
01/05/2026 - 7:16 PM
ACCELERATOR
MODEL
157
tokens/s
generation
236
ms
time to first token
5787
tokens/s
prompt
1566
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
15.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7531
tokens/s
137
tokens/s
148
ms
pp4096+tg256
4815
tokens/s
142
tokens/s
858
ms
pp2048+tg256
6208
tokens/s
152
tokens/s
337
ms
pp2048+tg768
6322
tokens/s
163
tokens/s
331
ms
pp1024+tg1024
7554
tokens/s
158
tokens/s
141
ms
pp1280+tg3072
6464
tokens/s
145
tokens/s
205
ms
pp384+tg1152
7944
tokens/s
163
tokens/s
55
ms
pp64+tg1024
4648
tokens/s
175
tokens/s
20
ms
pp16+tg1536
596
tokens/s
175
tokens/s
32
ms