TEST #2935 RESULTS
02/27/2026 - 7:35 PM
ACCELERATOR
MODEL
22.0
tokens/s
generation
18.03
sec
time to first token
83
tokens/s
prompt
47
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11370H @ 3.30GHz (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
55
tokens/s
14.2
tokens/s
18.73
sec
pp4096+tg256
70
tokens/s
18.8
tokens/s
58.64
sec
pp2048+tg256
65
tokens/s
26.5
tokens/s
31.58
sec
pp2048+tg768
87
tokens/s
23.5
tokens/s
23.46
sec
pp1024+tg1024
94
tokens/s
28.4
tokens/s
10.98
sec
pp1280+tg3072
92
tokens/s
23.9
tokens/s
13.97
sec
pp384+tg1152
97
tokens/s
11.4
tokens/s
4.01
sec
pp64+tg1024
101
tokens/s
27.2
tokens/s
665
ms
pp16+tg1536
85
tokens/s
24.2
tokens/s
220
ms