GP

gpt sw3 356m

GptGGUF by AI-Sweden-ModelsUpdated 2026-06-24
Download on Hugging Face
Parameters435M
Context2K
Layers—
Architecturegpt2
Smallest quant0.9 GB
Quick answer

gpt sw3 356m needs about 1.5 GB of memory at F16 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB (F16) to 1.7 GB (F32).

gpt sw3 356m is a 435M-parameter Gpt model in GGUF format, quantized by AI-Sweden-Models. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.9 GB (F16) to 1.7 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.9 GB 1.4 GB
Fits Get file →
F321.7 GB 2.3 GB
Fits Get file →

What GPU do you need for gpt sw3 356m?

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: the best quant that fits is F32 (1.7 GB file, about 2.5 GB in use).

Which gpt sw3 356m quant should you choose?

F16 (0.9 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

Architecturegpt2
Parameters435M
Trained context2,048 tokens

Source

Quantized byAI-Sweden-Models
FamilyGpt
Licenseother
Downloads (HF)0
Last updated2026-06-24

Frequently asked questions about gpt sw3 356m

How much VRAM does gpt sw3 356m need?

About 1.5 GB at F16 with an 8K context window. That is the 0.9 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 gpt sw3 356m on an 8 GB GPU?

Yes, with F32: the 1.7 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt sw3 356m GGUF?

It depends on the quant: F16 is 0.9 GB, F32 is 1.7 GB.

What context length does gpt sw3 356m support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download gpt sw3 356m GGUF?

The files are on Hugging Face in the AI-Sweden-Models/gpt-sw3-356m-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 gpt sw3 356m use?

Hugging Face lists the license as other. 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 AI-Sweden-Models

All by AI-Sweden-Models →

More Gpt models

All Gpt →

Other tiny models

All tiny models →