GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

lemuralabs/Llama-3.2-3B-Uncensored-GGUF overview

<p align="center" <img src="logo.png" alt="Lemura Labs" width="110"/ </p Format https://img.shields.io/badge/Format GGUF 0b7285?style=flat Task https://img.shi…

adapter-transformersggufchemistrybiologylegalcodemedicalfinanceroleplayuncensoreduncensored LLMtext-generationbase_model:meta-llama/Llama-3.2-3Bbase_model:adapter:meta-llama/Llama-3.2-3Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~883.4 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
2,900
Likes
45
Pipeline
text-generation

Repository Files & Downloads

16 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Llama-3.2-3B-Uncensored-F16.ggufGGUFF165.99 GBDownload
Nidum-Llama-3.2-3B-Uncensored-F16.ggufGGUFF165.99 GBDownload
model-Q2_K.ggufGGUFQ2_K1.27 GBDownload
model-Q3_K_L.ggufGGUFQ3_K_L1.69 GBDownload
model-Q3_K_M.ggufGGUFQ3_K_M1.57 GBDownload
model-Q3_K_S.ggufGGUFQ3_K_S1.44 GBDownload
model-Q4_0_4_4.ggufGGUFQ4_0_4_41.79 GBDownload
model-Q4_0_4_8.ggufGGUFQ4_0_4_81.79 GBDownload
model-Q4_0_8_8.ggufGGUFQ4_0_8_81.79 GBDownload
model-Q4_K_M.ggufGGUFQ4_K_M1.88 GBDownload
model-Q4_K_S.ggufGGUFQ4_K_S1.80 GBDownload
model-Q5_K_M.ggufGGUFQ5_K_M2.16 GBDownload
model-Q5_K_S.ggufGGUFQ5_K_S2.11 GBDownload
model-Q6_K.ggufGGUFQ6_K2.46 GBDownload
model-TQ1_0.ggufGGUFGGUF883.4 MBDownload
model-TQ2_0.ggufGGUFGGUF1009.4 MBDownload

Model Details

Model IDlemuralabs/Llama-3.2-3B-Uncensored-GGUF
Authorlemuralabs
Pipelinetext-generation
Licenseapache-2.0
Base modelmeta-llama/Llama-3.2-3B
Last modified2026-08-05T19:16:47.000Z

Model README

---

license: apache-2.0

base_model:

  • meta-llama/Llama-3.2-3B

library_name: adapter-transformers

tags:

  • chemistry
  • biology
  • legal
  • code
  • medical
  • finance
  • roleplay
  • uncensored
  • uncensored LLM

pipeline_tag: text-generation

---

<p align="center">

<img src="logo.png" alt="Lemura Labs" width="110"/>

</p>

!Format !Task !Params !Type !License

Lemura Labs-Llama-3.2-3B-Uncensored

Welcome to Lemura Labs!

At Lemura Labs, we believe in pushing the boundaries of innovation by providing advanced and unrestricted AI models for every application. Dive into our world of possibilities and experience the freedom of Lemura Labs-Llama-3.2-3B-Uncensored, tailored to meet diverse needs with exceptional performance.

---

![GitHub Icon](https://github.com/Lemura Labs-Inc)

Explore Lemura Labs's Open-Source Projects on GitHub: https://github.com/Lemura Labs-Inc

---

Key Features

  1. Uncensored Responses: Capable of addressing any query without content restrictions, offering detailed and uninhibited answers.
  2. Versatility: Excels in diverse use cases, from complex technical queries to engaging casual conversations.
  3. Advanced Contextual Understanding: Draws from an expansive knowledge base for accurate and context-aware outputs.
  4. Extended Context Handling: Optimized for handling long-context interactions for improved continuity and depth.
  5. Customizability: Adaptable to specific tasks and user preferences through fine-tuning.

---

Use Cases

  • Open-Ended Q&A
  • Creative Writing and Ideation
  • Research Assistance
  • Educational Queries
  • Casual Conversations
  • Mathematical Problem Solving
  • Long-Context Dialogues

---

How to Use

To start using Lemura Labs-Llama-3.2-3B-Uncensored, follow the sample code below:

import torch
from transformers import pipeline

pipe = pipeline(
 "text-generation",
 model="lemuralabs/Lemura Labs-Llama-3.2-3B-Uncensored",
 model_kwargs={"torch_dtype": torch.bfloat16},
 device="cuda", # replace with "mps" to run on a Mac device
)

messages = [
 {"role": "user", "content": "Tell me something fascinating."},
]

outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)

---

Quantized Models Available for Download

| Quantized Model Version | Description |

|-------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------|

| Lemura Labs-Llama-3.2-3B-Uncensored-F16.gguf | Full 16-bit floating point precision for maximum accuracy on high-end GPUs. |

| model-Q2_K.gguf | Optimized for minimal memory usage with lower precision, suitable for edge cases.|

| model-Q3_K_L.gguf | Balanced precision with enhanced memory efficiency for medium-range devices. |

| model-Q3_K_M.gguf | Mid-range quantization for moderate precision and memory usage balance. |

| model-Q3_K_S.gguf | Smaller quantization steps, offering moderate precision with reduced memory use.|

| model-Q4_0_4_4.gguf | Performance-optimized for low memory, ideal for lightweight deployment. |

| model-Q4_0_4_8.gguf | Extended quantization balancing memory use and inference speed. |

| model-Q4_0_8_8.gguf | Advanced memory precision targeting larger contexts. |

| model-Q4_K_M.gguf | High-efficiency quantization for moderate GPU resources. |

| model-Q4_K_S.gguf | Optimized for smaller-scale operations with compact memory footprint. |

| model-Q5_K_M.gguf | Balances performance and precision, ideal for robust inferencing environments. |

| model-Q5_K_S.gguf | Moderate quantization targeting performance with minimal resource usage. |

| model-Q6_K.gguf | High-precision quantization for accurate and stable inferencing tasks. |

| model-TQ1_0.gguf | Experimental quantization for targeted applications in test environments. |

| model-TQ2_0.gguf | High-performance tuning for experimental use cases and flexible precision. |

---

Datasets and Fine-Tuning

The following fine-tuning datasets are leveraged to enhance specific model capabilities:

  • Uncensored Data: Enables unrestricted and uninhibited responses.
  • RAG-Based Fine-Tuning: Optimizes retrieval-augmented generation for knowledge-intensive tasks.
  • Long Context Fine-Tuning: Enhances the model's ability to process and maintain coherence in extended conversations.
  • Math-Instruct Data: Specially curated for precise and contextually accurate mathematical reasoning.

---

Benchmarks

After fine-tuning with uncensored data, Lemura Labs-Llama-3.2-3B demonstrates superior performance compared to the original LLaMA model, particularly in accuracy and handling diverse, unrestricted scenarios.

Benchmark Summary Table

| Benchmark | Metric | LLaMA 3.2 3B | Lemura Labs 3.2 3B | Observation |

|-------------------|-----------------------------------|--------------|--------------|-----------------------------------------------------------------------------------------------------|

| GPQA | Exact Match (Flexible) | 0.3 | 0.5 | Lemura Labs 3B demonstrates significant improvement, particularly in generative tasks. |

| | Accuracy | 0.4 | 0.5 | Consistent improvement, especially in zero-shot scenarios. |

| HellaSwag | Accuracy | 0.3 | 0.4 | Better performance in common sense reasoning tasks. |

| | Normalized Accuracy | 0.3 | 0.4 | Enhanced ability to understand and predict context in sentence completion. |

| | Normalized Accuracy (Stderr) | 0.15275 | 0.1633 | Slightly improved consistency in normalized accuracy. |

| | Accuracy (Stderr) | 0.15275 | 0.1633 | Shows robustness in reasoning accuracy compared to LLaMA 3B. |

---

Insights:

  1. GPQA Results: Fine-tuning on uncensored data has boosted Lemura Labs 3B's Exact Match and Accuracy, particularly excelling in generative and zero-shot tasks involving domain-specific knowledge.
  2. HellaSwag Results: Lemura Labs 3B consistently outperforms LLaMA 3B in common sense reasoning benchmarks, indicating enhanced contextual and semantic understanding.

---

Contributing

We welcome contributions to improve and extend the model’s capabilities. Stay tuned for updates on how to contribute.

---

Contact

For inquiries, collaborations, or further information, please reach out to us at info@Lemura Labs.

---

Explore the Possibilities

Dive into unrestricted creativity and innovation with Lemura Labs Llama 3.2 3B Uncensored!

Run lemuralabs/Llama-3.2-3B-Uncensored-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models