LL

Nidum Llama 3.2 3B Uncensored

LlamaGGUF by lemuralabsUpdated 2026-08-05
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant0.9 GB
Quick answer

Nidum Llama 3.2 3B Uncensored needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 16 quants, from 0.9 GB (TQ1_0) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Nidum Llama 3.2 3B Uncensored – a 3‑billion‑parameter Llama model with extended context and uncensored responses

Nidum Llama 3.2 3B Uncensored is a 3‑billion‑parameter Llama model trained on 131,072 context tokens. It supports coding and roleplay tasks and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for efficient local deployment.

Good at

  • Coding assistance
  • Roleplay conversations
  • Long‑context dialogue

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • Uncensored content may produce unrestricted outputs

Best for

  • Local LLM deployment
  • Educational Q&A
  • Creative writing

Who it’s for. Developers and researchers who need a lightweight, uncensored Llama model for local inference. The model is suitable for applications that require extended context handling and flexible fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_00.9 GB 2.4 GB
Fits Get file →
TQ2_01.1 GB 2.5 GB
Fits Get file →
Q2_K1.4 GB 2.8 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q3_K_L1.8 GB 3.3 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_K_S1.9 GB 3.4 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q5_K_S2.3 GB 3.7 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →
F166.4 GB 7.9 GB
Tight Get file →

For 8‑GB VRAM, use Q4_K_M (2.02 GB file, ~3.5 GB VRAM). For 12‑GB VRAM, Q5_K_M (2.32 GB file, ~3.8 GB VRAM) offers higher quality. If more VRAM is available, F16 (6.43 GB file, ~7.9 GB VRAM) provides full‑precision performance.

What GPU do you need for Nidum Llama 3.2 3B Uncensored?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q5_K_M (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (2.6 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).

Which Nidum Llama 3.2 3B Uncensored quant should you choose?

Q4_K_M is the usual starting point for Nidum Llama 3.2 3B Uncensored: it balances file size and quality well. Here it is a 2.0 GB file.

If memory is tight, the smallest file is TQ1_0 at 0.9 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bylemuralabs
FamilyLlama
Licenseapache-2.0
Downloads (HF)13,031
Last updated2026-08-05

Frequently asked questions about Nidum Llama 3.2 3B Uncensored

How much VRAM does Nidum Llama 3.2 3B Uncensored need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Nidum Llama 3.2 3B Uncensored on an 8 GB GPU?

Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nidum Llama 3.2 3B Uncensored GGUF?

It depends on the quant: TQ1_0 is 0.9 GB, TQ2_0 is 1.1 GB, Q2_K is 1.4 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.7 GB, Q3_K_L is 1.8 GB and 10 more.

What context length does Nidum Llama 3.2 3B Uncensored support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Nidum Llama 3.2 3B Uncensored GGUF?

The files are on Hugging Face in the lemuralabs/Llama-3.2-3B-Uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nidum Llama 3.2 3B Uncensored use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Nidum Llama 3.2 3B Uncensored on 8 GB VRAM?

Yes, a Q4_K_M quantized file (~2.02 GB) will fit and use about 3.5 GB VRAM at 8‑k context.

Does the model support vision tasks?

No, the model is purely text‑based and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of Llama-3.2-3B

Similar models

Browse all →

More from lemuralabs

All by lemuralabs →

More Llama models

All Llama →

Other tiny models

All tiny models →