LO

local

LocalGGUF by angchemyUpdated 2026-03-26
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant3.2 GB
Quick answer

local needs about 4.8 GB of memory at Q4_0 (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

local is a 3.88B-parameter Local model in GGUF format, quantized by angchemy. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.2 GB (Q4_0) to 3.2 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_03.2 GB 4.8 GB
Fits Get file →

What GPU do you need for local?

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: the best quant that fits is Q4_0 (3.2 GB file, about 4.8 GB in use).

Which local quant should you choose?

Q4_0 (3.2 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

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized byangchemy
FamilyLocal
Repositoryangchemy/local
Licensemit
Downloads (HF)2
Last updated2026-03-26

Frequently asked questions about local

How much VRAM does local need?

About 4.8 GB at Q4_0 with an 8K context window. That is the 3.2 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 local on an 8 GB GPU?

Yes, with Q4_0: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of local GGUF?

It depends on the quant: Q4_0 is 3.2 GB.

What context length does local support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download local GGUF?

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

What license does local 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.

Similar models

Browse all →

More Local models

All Local →

Other small models

All small models →