LL

Llama 3.2 3B

LlamaGGUF by bagasbgs2516Updated 2024-12-13
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant12.9 GB
Quick answer

Llama 3.2 3B needs about 14.3 GB of memory at its main file (a 12.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B is a 3.21B-parameter Llama model in GGUF format, quantized by bagasbgs2516. Its trained context length is 128K tokens. The repository has 1 quant file, from 12.9 GB to 12.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.9 GB 14.3 GB
Too big Get file →

What GPU do you need for Llama 3.2 3B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (12.9 GB file, about 14.3 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 bybagasbgs2516
FamilyLlama
Downloads (HF)6
Last updated2024-12-13

Frequently asked questions about Llama 3.2 3B

How much VRAM does Llama 3.2 3B need?

About 14.3 GB at its main file with an 8K context window. That is the 12.9 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 Llama 3.2 3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.2 3B GGUF?

It depends on the quant: file is 12.9 GB.

What context length does Llama 3.2 3B 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 GGUF?

The files are on Hugging Face in the bagasbgs2516/llama3.2-3B-cs-Tokyo8 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Llama-3.2-3B

Similar models

Browse all →

More from bagasbgs2516

All by bagasbgs2516 →

More Llama models

All Llama →

Other tiny models

All tiny models →