LL

WizardLM llama3.2 3b IQ4 NL

LlamaGGUF by PJRMUpdated 2026-05-27
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.9 GB
Quick answer

WizardLM llama3.2 3b IQ4 NL needs about 3.4 GB of memory at IQ4_NL (a 1.9 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.

WizardLM llama3.2 3b IQ4 NL is a 3.21B-parameter Llama model in GGUF format, quantized by PJRM. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.9 GB (IQ4_NL) to 1.9 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL1.9 GB 3.4 GB
Fits Get file →

What GPU do you need for WizardLM llama3.2 3b IQ4 NL?

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 IQ4_NL (1.9 GB file, about 3.4 GB in use).

Which WizardLM llama3.2 3b IQ4 NL quant should you choose?

IQ4_NL (1.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 byPJRM
FamilyLlama
Licenseapache-2.0
Downloads (HF)31
Last updated2026-05-27

Frequently asked questions about WizardLM llama3.2 3b IQ4 NL

How much VRAM does WizardLM llama3.2 3b IQ4 NL need?

About 3.4 GB at IQ4_NL with an 8K context window. That is the 1.9 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 WizardLM llama3.2 3b IQ4 NL on an 8 GB GPU?

Yes, with IQ4_NL: the 1.9 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WizardLM llama3.2 3b IQ4 NL GGUF?

It depends on the quant: IQ4_NL is 1.9 GB.

What context length does WizardLM llama3.2 3b IQ4 NL 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 WizardLM llama3.2 3b IQ4 NL GGUF?

The files are on Hugging Face in the PJRM/WizardLM-llama3.2-3b-IQ4_NL-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 WizardLM llama3.2 3b IQ4 NL 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.

Other GGUFs of WizardLM-llama3.2-3b

Similar models

Browse all →

More from PJRM

All by PJRM →

More Llama models

All Llama →

Other tiny models

All tiny models →