Llama 3.2 3B Instruct DASHQ Q2 needs about 2.6 GB of memory at IQ2_XS (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.0 GB (IQ2_XXS) to 1.3 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llama 3.2 3B Instruct DASHQ 2‑bit quantized model
Llama 3.2 3B Instruct DASHQ Q2 is a 3.21 billion‑parameter Llama model quantized to 2‑bit with DASH‑Q. It supports tool usage and runs on recent llama.cpp builds. The model offers a 131072‑token context window.
Good at
- Tool integration
- Low‑memory inference
- Fast token generation
Limits
- No vision support
- Requires recent llama.cpp build
- License is llama3.2
Best for
- Embedded inference
- Edge devices with limited VRAM
- Rapid prototyping
Who it’s for. Developers needing a compact Llama 3.2 model for local deployment. The 2‑bit quantization makes it suitable for systems with limited GPU memory while retaining instruction following capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ2_XS | 1.1 GB | 2.6 GB | Fits | Get file → | |
| IQ2_M | 1.2 GB | 2.6 GB | Fits | Get file → | |
| Q2_K_XL | 1.3 GB | 2.7 GB | Fits | Get file → |
For 8 GB VRAM, use IQ2_XXS (1 GB file, ~2.4 GB memory at 8 k context). If 10 GB VRAM is available, IQ2_XS (1.14 GB, ~2.6 GB) or IQ2_M (1.21 GB, ~2.6 GB) are suitable. For 12 GB VRAM, Q2_K_XL (1.31 GB, ~2.7 GB) offers the best quality.
What GPU do you need for Llama 3.2 3B Instruct DASHQ Q2?
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 Q2_K_XL (1.3 GB file, about 2.7 GB in use).
Which Llama 3.2 3B Instruct DASHQ Q2 quant should you choose?
IQ2_XS (1.1 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 1.0 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
Source
Frequently asked questions about Llama 3.2 3B Instruct DASHQ Q2
How much VRAM does Llama 3.2 3B Instruct DASHQ Q2 need?
About 2.6 GB at IQ2_XS with an 8K context window. That is the 1.1 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 DASHQ Q2 on an 8 GB GPU?
Yes, with Q2_K_XL: the 1.3 GB file needs about 2.7 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 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_M is 1.2 GB, Q2_K_XL is 1.3 GB.
What context length does Llama 3.2 3B Instruct DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/Llama-3.2-3B-Instruct-DASHQ-Q2-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 DASHQ Q2 use?
Hugging Face lists the license as llama3.2. 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, the IQ2_XXS quantization uses about 2.4 GB at 8 k context, fitting comfortably in 8 GB VRAM.
Does this model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
It inherits the llama3.2 license from the base model.