Llama 3.2 3B Instruct 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 25 quants, from 0.9 GB (IQ1_S) to 2.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llama 3.2 3B Instruct – a 3 B parameter model with 128k context and horror‑enhanced creativity
Llama 3.2 3B Instruct is a 3 B parameter instruction model with a maximum context of 131 072 tokens. It is trained on the NEO IMATRIX Tiny “Wee” Horror Dataset, which adds a horror tint to prompts and increases vividness. The model runs on llama.cpp and supports temperature settings from 0 to 5.
Good at
- Horror‑enhanced storytelling
- Creative role‑play with vivid detail
- Instruction following with high temperature flexibility
Limits
- Large context requires high VRAM
- No vision or multimodal support
- Requires llama.cpp template
Best for
- Writing horror scenes
- Generating creative role‑play scripts
- Testing temperature effects on prose
Who it’s for. Developers and hobbyists who want a compact Llama 3.2 model with a horror‑focused dataset. The model is suitable for local inference on GPUs with sufficient VRAM and for experimentation with different temperature settings.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| IQ2_XXS | 1.0 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XS | 1.1 GB | 2.5 GB | Fits | Get file → | |
| IQ2_S | 1.2 GB | 2.6 GB | Fits | Get file → | |
| IQ2_M | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q2_K_S | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XXS | 1.3 GB | 2.8 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.9 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 3.0 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.4 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 4.1 GB | Fits | Get file → |
For 8 GB VRAM, use IQ2_S (1.15 GB file, ~2.6 GB VRAM at 8 k context). For 12 GB VRAM, IQ4_XS (1.83 GB file, ~3.3 GB VRAM) offers the strongest Imatrix effect. For 16 GB VRAM, Q5_K_M (2.32 GB file, ~3.8 GB VRAM) provides a balance between quality and memory.
What GPU do you need for Llama 3.2 3B Instruct?
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).
Which Llama 3.2 3B Instruct quant should you choose?
Q4_K_M is the usual starting point for Llama 3.2 3B Instruct: it balances file size and quality well. Here it is a 2.0 GB file.
If memory is tight, the smallest file is IQ1_S at 0.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Llama 3.2 3B Instruct
How much VRAM does Llama 3.2 3B Instruct 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 Llama 3.2 3B Instruct on an 8 GB GPU?
Yes, with Q6_K: the 2.6 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3.2 3B Instruct GGUF?
It depends on the quant: IQ1_S is 0.9 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.2 GB, IQ2_M is 1.2 GB and 19 more.
What context length does Llama 3.2 3B Instruct 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 Llama 3.2 3B Instruct GGUF?
The files are on Hugging Face in the DavidAU/Llama-3.2-3B-Instruct-NEO-WEE-HORROR-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 Llama 3.2 3B Instruct 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 this model on 8 GB VRAM?
Yes, using IQ2_S or IQ2_XS quants will fit within 8 GB VRAM, with estimated usage around 2.5 GB at 8 k context.
Does this model support image input?
No, the model is text‑only and has no vision or multimodal capabilities.
What template should I use with llama.cpp?
Use the standard Llama 3 template; other templates may produce different outputs.