LL

Llama3.2 3B ShiningValiant2

LlamaGGUF by RichardErkhovUpdated 2024-10-16
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.4 GB
Quick answer

Llama3.2 3B ShiningValiant2 needs about 2.9 GB of memory at IQ3_XS (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB (Q2_K) to 1.5 GB (Q3_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama3.2 3B ShiningValiant2 is a 3.21B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 4 quant files, from 1.4 GB (Q2_K) to 1.5 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 2.8 GB
Fits Get file →
IQ3_XS1.5 GB 2.9 GB
Fits Get file →
IQ3_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →

What GPU do you need for Llama3.2 3B ShiningValiant2?

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 IQ3_S (1.5 GB file, about 3.0 GB in use).

Which Llama3.2 3B ShiningValiant2 quant should you choose?

IQ3_XS (1.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byRichardErkhov
FamilyLlama
Licensellama3.2
Downloads (HF)27
Last updated2024-10-16

Frequently asked questions about Llama3.2 3B ShiningValiant2

How much VRAM does Llama3.2 3B ShiningValiant2 need?

About 2.9 GB at IQ3_XS with an 8K context window. That is the 1.5 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 ShiningValiant2 on an 8 GB GPU?

Yes, with IQ3_S: the 1.5 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama3.2 3B ShiningValiant2 GGUF?

It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.5 GB, IQ3_S is 1.5 GB, Q3_K_S is 1.5 GB.

What context length does Llama3.2 3B ShiningValiant2 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 3B ShiningValiant2 GGUF?

The files are on Hugging Face in the RichardErkhov/ValiantLabs_-_Llama3.2-3B-ShiningValiant2-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 Llama3.2 3B ShiningValiant2 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 from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other tiny models

All tiny models →