modelbenchmark.io

Llama 3.2 3B Uncensored

Meta · llama-32-3b-uncensored

Compare

Refusal-ablated Llama 3.2 3B Instruct, served as GGUF: it answers prompts the stock instruct model declines, keeping the same 128k context and multilingual behaviour.

Specification

most-agreed values

Context
131K
Max output
131K
Released
2024-09-25
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
$3.00

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
autarchofree$3.00——131K131K—

More from Meta

most-hosted first