LL

llama3.2 for chat

LlamaGGUF by jj8127Updated 2024-11-07
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.1 GB
Quick answer

llama3.2 for chat needs about 3.5 GB of memory at Q4_1 (a 2.1 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.

llama3.2 for chat is a 3.21B-parameter Llama model in GGUF format, quantized by jj8127. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.1 GB (Q4_1) to 2.1 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_12.1 GB 3.5 GB
Fits Get file →

What GPU do you need for llama3.2 for chat?

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 Q4_1 (2.1 GB file, about 3.5 GB in use).

Which llama3.2 for chat quant should you choose?

Q4_1 (2.1 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 byjj8127
FamilyLlama
Licensellama3.2
Downloads (HF)3
Last updated2024-11-07

Frequently asked questions about llama3.2 for chat

How much VRAM does llama3.2 for chat need?

About 3.5 GB at Q4_1 with an 8K context window. That is the 2.1 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 for chat on an 8 GB GPU?

Yes, with Q4_1: the 2.1 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 llama3.2 for chat GGUF?

It depends on the quant: Q4_1 is 2.1 GB.

What context length does llama3.2 for chat 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 llama3.2 for chat GGUF?

The files are on Hugging Face in the jj8127/llama3.2_for_chat repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does llama3.2 for chat 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.

Similar models

Browse all →

More Llama models

All Llama →

Other tiny models

All tiny models →