Llama 3.2 3B Instruct IQ3 M needs about 3.0 GB of memory at IQ3_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llama 3.2 3B Instruct IQ3 M is a 3.21B-parameter Llama model in GGUF format, quantized by zanish-labs. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.6 GB (IQ3_M) to 1.6 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 1.6 GB | 3.0 GB | Fits | Get file → |
What GPU do you need for Llama 3.2 3B Instruct IQ3 M?
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 IQ3_M (1.6 GB file, about 3.0 GB in use).
Which Llama 3.2 3B Instruct IQ3 M quant should you choose?
IQ3_M (1.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3.2 3B Instruct IQ3 M
How much VRAM does Llama 3.2 3B Instruct IQ3 M need?
About 3.0 GB at IQ3_M with an 8K context window. That is the 1.6 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 IQ3 M on an 8 GB GPU?
Yes, with IQ3_M: the 1.6 GB file needs about 3.0 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 IQ3 M GGUF?
It depends on the quant: IQ3_M is 1.6 GB.
What context length does Llama 3.2 3B Instruct IQ3 M 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 IQ3 M GGUF?
The files are on Hugging Face in the zanish-labs/Llama-3.2-3B-Instruct-IQ3_M-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 IQ3 M 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.