TI

Moonlit-SummaryStories-45M

TinystoriesGGUF by razor5050Updated 2026-05-23
Download on Hugging Face
Parameters46M
Context512
Layers13
Architecturellama
Smallest quant0.0 GB
Quick answer

Moonlit-SummaryStories-45M needs about 0.6 GB of memory at Q5_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.0 GB (Q5_K_M) to 0.2 GB (F32).

Moonlit-SummaryStories-45M is a 46M-parameter Tinystories model in GGUF format, quantized by razor5050. Its trained context length is 512 tokens. The repository has 2 quant files, from 0.0 GB (Q5_K_M) to 0.2 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.0 GB 0.5 GB
Fits Get file →
F320.2 GB 0.7 GB
Fits Get file →

What GPU do you need for Moonlit-SummaryStories-45M?

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 F32 (0.2 GB file, about 0.8 GB in use).

Which Moonlit-SummaryStories-45M quant should you choose?

Q5_K_M (0.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters46M
Layers13
Trained context512 tokens
KV cache (fp16)13 KB per token

Source

Quantized byrazor5050
Licenseapache-2.0
Downloads (HF)76
Last updated2026-05-23

Frequently asked questions about Moonlit-SummaryStories-45M

How much VRAM does Moonlit-SummaryStories-45M need?

About 0.6 GB at Q5_K_M with an 8K context window. That is the 0.0 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 Moonlit-SummaryStories-45M on an 8 GB GPU?

Yes, with F32: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Moonlit-SummaryStories-45M GGUF?

It depends on the quant: Q5_K_M is 0.0 GB, F32 is 0.2 GB.

What context length does Moonlit-SummaryStories-45M support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.

Where can I download Moonlit-SummaryStories-45M GGUF?

The files are on Hugging Face in the razor5050/Moonlit-SummaryStories-45M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Moonlit-SummaryStories-45M use?

Hugging Face lists the license as apache-2.0. 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 Tinystories models

All Tinystories →

Other tiny models

All tiny models →