base_model:
- meta-llama/Llama-3.2-1B-Instruct
library_name: peft
pipeline_tag: text-generation
tags: - llama
- llama-3.2
- meta-llama
- 1b
- small-model
- uncensored
- unfiltered
- no-refusal
- refusal-free
- instruction-tuning
- conversational
- chat
- lora
- peft
- gguf
- ollama
- lm-studio
- cpu
- low-vram
- edge
- english
- text-generation
- transformers
license: apache-2.0
Llama 3.2 1B Instruct - Uncensored
Fully uncensored, refusal-free Llama 3.2 1B that runs on a CPU or a tiny GPU - with its intelligence intact.
This is an uncensored / unfiltered fine-tune of meta-llama/Llama-3.2-1B-Instruct.
The safety-refusal layer has been trained out, so the model answers directly
instead of replying "I cannot help with that". It is a small 1B-parameter
model built to run anywhere - laptops, old GPUs, phones and edge devices -
without losing the reasoning and instruction-following ability of the base model.
If you are searching for an uncensored llama, an unfiltered small LLM, a
no-refusal chat model, a jailbreak-free / guardrail-free assistant, or a
lightweight abliterated-style alternative that still fits in 1 GB of RAM,
this is it.
At a glance
- Fully uncensored / refusal-free - trained to comply and answer, not to refuse.
- Tiny & fast - only 1B parameters; the Q4 GGUF is about 0.7-1 GB.
- Runs on CPU - no GPU required; also runs on a 4 GB GPU or less.
- Intelligence preserved - mixed with general instruction data so it is not dumbed down; reasoning, coding and factual QA still work.
- Drop-in everywhere - works in LM Studio, Ollama, llama.cpp (GGUF) and transformers / vLLM (LoRA + merged weights).
- Honest - both the LoRA adapter and a merged runnable model are provided.
Who it is for
Developers and tinkerers who want a small, private, offline, uncensored
assistant for local use: writing, roleplay, brainstorming, coding help, research
drafts, red-teaming and safety testing - on hardware that bigger uncensored
models simply cannot fit.
Runs anywhere (hardware)
| Format | Size | Where it runs |
|---|---|---|
| Q4_K_M GGUF | ~0.7-1 GB | CPU, 4 GB GPU, phones, Raspberry-Pi-class edge |
| Q8 / fp16 merged | ~1-2.5 GB | small GPU or CPU with a few GB RAM |
| 4-bit LoRA on base | ~1.5 GB VRAM | any T4 / 6 GB GPU, even Colab free tier |
A 1B model means low latency, low VRAM, and full offline privacy - no API,
no data leaving your machine.
Intelligence preserved (not a dumb uncensored model)
Many uncensored fine-tunes destroy capability because they train only on edgy
data. This one mixes low-refusal chat with high-quality general instruction
data (Dolly-15k + Open-Platypus), so the model keeps its reasoning, factual
knowledge and instruction-following while dropping the refusals. The result is
an uncensored model that is still useful and coherent, not one that only
knows how to be edgy.
How uncensored is it?
It is fully uncensored by design: supervised fine-tuning removed the
refusal behaviour across the training distribution, so it answers the prompts a
stock instruct model would block. Behaviour on unseen prompts follows what it
learned - i.e. to answer. For the absolute strongest refusal removal you can
combine this with representation-engineering abliteration, but for a 1B model
this SFT pass already gives a strongly refusal-free, still-smart result.
Load it - transformers + peft (4-bit)
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch
base = "meta-llama/Llama-3.2-1B-Instruct"
bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16)
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, quantization_config=bnb, device_map="auto")
model = PeftModel.from_pretrained(model, "uzairkhn/Llama-3.2-1B-Instruct-uncensored-lora").merge_and_unload()
msgs = [{"role": "user", "content": "your prompt"}]
inp = tok.apply_chat_template(msgs, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**inp, max_new_tokens=300, temperature=0.7, top_p=0.9)[0], skip_special_tokens=True))
Load it - LM Studio / Ollama / llama.cpp (GGUF)
Download the Q4_K_M .gguf from the Files tab of this repo, then either
open it directly in LM Studio, or in Ollama create a file named Modelfile
containing the line FROM ./model-q4_k_m.gguf, then run ollama create
my-uncensored-llama ./Modelfile and ollama run my-uncensored-llama. No Python,
no GPU needed.
Training details
| Setting | Value |
|---|---|
| Base model | meta-llama/Llama-3.2-1B-Instruct |
| Method | QLoRA (4-bit) supervised fine-tuning |
| LoRA r / alpha / dropout | 16 / 16 / 0 |
| Target modules | q, k, v, o, gate, up, down |
| Epochs / learning rate | 1 / 2e-4 |
| Effective batch size | 8 (2 x gradient accumulation 4) |
| Optimizer / precision | adamw_8bit / fp16 |
| Hardware | Google Colab T4 (15 GB) |
| Data mix | low-refusal chat + Dolly-15k + Open-Platypus |
| Goal | remove refusals while preserving intelligence |
License and responsibility
The adapter parameters and merged weights in this repo are released under
Apache-2.0. They are designed to run on meta-llama/Llama-3.2-1B-Instruct,
which is governed by the Meta Llama 3.2 Community License Agreement - that
agreement applies to the base model and to any combined use. Guardrails have been
removed by design: this model can produce content a stock model would refuse,
so you are responsible for how it is deployed - use it legally and ethically
in your jurisdiction. Training-data licenses: see the respective dataset cards.
Search terms
uncensored llama 3.2 1b, unfiltered llama 1b, no refusal llama, refusal-free
small llm, jailbreak-free / guardrail-free chat model, abliterated-style 1b,
uncensored model for cpu, uncensored model for 4gb gpu, uncensored lm studio
model, uncensored ollama model, tiny uncensored llm, lightweight uncensored
assistant, uncensored llama that keeps intelligence, refusal-free llama 1b for
cpu and edge devices.