LL

llama3.2 3B fp16 BE

LlamaGGUF by prajwal-ibmUpdated 2025-02-13
Download on Hugging Face
Parameters3.61B
Context128K
Layers—
Architecturellama
Smallest quant7.2 GB
Quick answer

llama3.2 3B fp16 BE needs about 8.6 GB of memory at F16 (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.

llama3.2 3B fp16 BE is a 3.61B-parameter Llama model in GGUF format, quantized by prajwal-ibm. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.2 GB (F16) to 7.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F167.2 GB 8.6 GB
Too big Get file →

What GPU do you need for llama3.2 3B fp16 BE?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F16 (7.2 GB file, about 8.6 GB in use).

Which llama3.2 3B fp16 BE quant should you choose?

F16 (7.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.61B
Trained context131,072 tokens

Source

Quantized byprajwal-ibm
FamilyLlama
Downloads (HF)4
Last updated2025-02-13

Frequently asked questions about llama3.2 3B fp16 BE

How much VRAM does llama3.2 3B fp16 BE need?

About 8.6 GB at F16 with an 8K context window. That is the 7.2 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 llama3.2 3B fp16 BE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama3.2 3B fp16 BE GGUF?

It depends on the quant: F16 is 7.2 GB.

What context length does llama3.2 3B fp16 BE support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download llama3.2 3B fp16 BE GGUF?

The files are on Hugging Face in the prajwal-ibm/llama3.2-3B-fp16-BE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from prajwal-ibm

All by prajwal-ibm →

More Llama models

All Llama →

Other small models

All small models →