LL

LlamaLite 3B TQ2 0

LlamaGGUF by sagar27kumarUpdated 2025-03-10
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.5 GB
Quick answer

LlamaLite 3B TQ2 0 needs about 3.0 GB of memory at TQ2_0 (a 1.5 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.

LlamaLite 3B TQ2 0 is a 3.21B-parameter Llama model in GGUF format, quantized by sagar27kumar. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.5 GB (TQ2_0) to 1.5 GB (TQ2_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_01.5 GB 3.0 GB
Fits Get file →

What GPU do you need for LlamaLite 3B TQ2 0?

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 TQ2_0 (1.5 GB file, about 3.0 GB in use).

Which LlamaLite 3B TQ2 0 quant should you choose?

TQ2_0 (1.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

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 bysagar27kumar
FamilyLlama
Licensemit
Downloads (HF)13
Last updated2025-03-10

Frequently asked questions about LlamaLite 3B TQ2 0

How much VRAM does LlamaLite 3B TQ2 0 need?

About 3.0 GB at TQ2_0 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 LlamaLite 3B TQ2 0 on an 8 GB GPU?

Yes, with TQ2_0: 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 LlamaLite 3B TQ2 0 GGUF?

It depends on the quant: TQ2_0 is 1.5 GB.

What context length does LlamaLite 3B TQ2 0 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 LlamaLite 3B TQ2 0 GGUF?

The files are on Hugging Face in the sagar27kumar/LlamaLite-3B-TQ2_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does LlamaLite 3B TQ2 0 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Llama-3.2-3B-Instruct

Similar models

Browse all →

More from sagar27kumar

All by sagar27kumar →

More Llama models

All Llama →

Other tiny models

All tiny models →