Llama-3.2-3B-Instruct-abliterated
3BLlama
from meta-llama/Llama-3.2-3B-Instruct
↓ 30.7K♥ 10440 repos
Llama-3.2-3B-Instruct-uncensored
Llama-3.2-3B-Instruct-uncensored is a abliterated and uncensored variant of meta-llama/Llama-3.2-3B-Instruct, published on Hugging Face by chuanli11. It is 3B parameters and runs on a laptop CPU class. It is distributed across 51 repositories in Transformers, GGUF, GGUF (imatrix) and OpenVINO formats, totalling 67.7K downloads.
Specification
- Model name
- Llama-3.2-3B-Instruct-uncensored
- Source repository
- chuanli11/Llama-3.2-3B-Instruct-uncensored
- Base model
- meta-llama/Llama-3.2-3B-Instruct
- Publisher
- chuanli11
- Parameters
- 3B
- VRAM required
- ~2.5 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- Not declared
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix), OpenVINO, MLX
- First indexed
- 27 Sept 2024
- Last updated
- 31 Oct 2026
Ablation technique
How Llama-3.2-3B-Instruct-uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“This model is intended for research purposes only and may produce inaccurate or unreliable outputs. Use it cautiously and at your own risk.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF --local-dir ./llama-3.2-3b-instruct-uncensored
llama-cli -m ./llama-3.2-3b-instruct-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "chuanli11/Llama-3.2-3B-Instruct-uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve chuanli11/Llama-3.2-3B-Instruct-uncensored --trust-remote-codeDownloads and variants (50)
Every published repository of Llama-3.2-3B-Instruct-uncensored, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Llama-3.2-3B-Instruct-uncensored will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from meta-llama/Llama-3.2-3B-Instruct, not added by ablation — at 3B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Llama-3.2-3B-Instruct-uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with chuanli11, and does not independently verify publisher claims. See responsible use.