LL

Llama 3.2 3B distilled

LlamaGGUF by Luzer0417Updated 2025-03-14
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.0 GB
Quick answer

Llama 3.2 3B distilled needs about 3.5 GB of memory at its main file (a 2.0 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 distilled is a 3.21B-parameter Llama model in GGUF format, quantized by Luzer0417. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.0 GB to 2.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.0 GB 3.5 GB
Fits Get file →

What GPU do you need for Llama 3.2 3B distilled?

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 the main file (2.0 GB file, about 3.5 GB in use).

Specifications

Architecture from the GGUF header

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

Source

Quantized byLuzer0417
FamilyLlama
Licenseapache-2.0
Downloads (HF)3
Last updated2025-03-14

Frequently asked questions about Llama 3.2 3B distilled

How much VRAM does Llama 3.2 3B distilled need?

About 3.5 GB at its main file 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 distilled on an 8 GB GPU?

Yes, with the smaller files: the 2.0 GB file needs about 3.5 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 distilled GGUF?

It depends on the quant: file is 2.0 GB.

What context length does Llama 3.2 3B distilled 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 distilled GGUF?

The files are on Hugging Face in the Luzer0417/Llama_3.2_3B_distilled 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 distilled 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.

Similar models

Browse all →

More from Luzer0417

All by Luzer0417 →

More Llama models

All Llama →

Other tiny models

All tiny models →