TI

TinyStories-656K

TinystoriesGGUF by raincandy-uUpdated 2024-06-12
Download on Hugging Face
Parameters—
Context512
Layers2
Architecturellama
Smallest quant0.0 GB
Quick answer

TinyStories-656K needs about 0.5 GB of memory at Q8_0 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

TinyStories-656K: a 600k‑parameter story generation model

TinyStories-656K is a llama architecture language model trained from scratch on the TinyStoriesV2 dataset. It contains only 2 transformer layers and a hidden size of 128, designed for lightweight story generation.

Good at

  • Story generation
  • Low‑parameter inference
  • Simple architecture

Limits

  • Small context of 512 tokens
  • Requires 0.5 GB VRAM at 8 k context
  • No vision support

Best for

  • Generating short stories
  • Testing lightweight LLMs
  • Educational demos

Who it’s for. Developers and hobbyists looking for a minimal LLM that can run on modest hardware. It is suitable for experimentation and educational purposes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 0.5 GB
Fits Get file →

The Q8_0 quantization is the only available file. It requires approximately 0.5 GB VRAM at 8 k context. For systems with less VRAM, consider using a smaller context or a different quantization if available.

What GPU do you need for TinyStories-656K?

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 Q8_0 (0.0 GB file, about 0.5 GB in use).

Which TinyStories-656K quant should you choose?

Q8_0 (0.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Layers2
Trained context512 tokens
KV cache (fp16)1 KB per token

Source

Quantized byraincandy-u
Licenseapache-2.0
Downloads (HF)1,684
Last updated2024-06-12

Frequently asked questions about TinyStories-656K

How much VRAM does TinyStories-656K need?

About 0.5 GB at Q8_0 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 TinyStories-656K on an 8 GB GPU?

Yes, with Q8_0: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyStories-656K GGUF?

It depends on the quant: Q8_0 is 0.0 GB.

What context length does TinyStories-656K support?

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

Where can I download TinyStories-656K GGUF?

The files are on Hugging Face in the raincandy-u/TinyStories-656K-Q8_0-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 TinyStories-656K 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.

Can I run TinyStories-656K on 8 GB VRAM?

Yes, the Q8_0 quantization needs about 0.5 GB VRAM at 8 k context, well within an 8 GB budget.

Does TinyStories-656K support vision tasks?

No, it is a text‑only language model with no vision capabilities.

Other GGUFs of TinyStories-656K

More from raincandy-u

All by raincandy-u →

More Tinystories models

All Tinystories →