Raincandy U TinyStories 656K needs about 0.5 GB of memory at Q2_K (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 (Q2_K) to 0.0 GB (Q3_K_M).
TinyStories-656K: a 600k‑parameter story generation model
Raincandy U TinyStories 656K is a small Llama‑based language model trained from scratch on TinyStoriesV2. It has 2 transformer layers and a hidden size of 128. The model is available in GGUF format and is compatible with llama.cpp.
Good at
- Story generation
- Low‑parameter inference
- Simple prompt handling
Limits
- 512 token context
- No vision support
- Apache‑2.0 license
Best for
- Embedded storytelling apps
- Educational content creation
- Rapid prototyping of narrative models
Who it’s for. Developers needing a lightweight story generator that can run on modest hardware. The model is suitable for projects that require quick inference without large GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q2_K or Q3_K_M; each requires about 0.5 GB of VRAM at 8 k context. Both are small enough for low‑end GPUs. Choose Q2_K for slightly lower memory usage.
What GPU do you need for Raincandy U 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 Q3_K_M (0.0 GB file, about 0.5 GB in use).
Which Raincandy U TinyStories 656K quant should you choose?
Q2_K (0.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Raincandy U TinyStories 656K
How much VRAM does Raincandy U TinyStories 656K need?
About 0.5 GB at Q2_K 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 Raincandy U TinyStories 656K on an 8 GB GPU?
Yes, with Q3_K_M: 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 Raincandy U TinyStories 656K GGUF?
It depends on the quant: Q2_K is 0.0 GB, Q3_K_M is 0.0 GB.
What context length does Raincandy U 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 Raincandy U TinyStories 656K GGUF?
The files are on Hugging Face in the tensorblock/TinyStories-656K-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 Raincandy U 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. Both Q2_K and Q3_K_M quantizations need about 0.5 GB of VRAM at 8 k context, well within an 8 GB GPU.
What license does TinyStories-656K use?
The model is released under the Apache‑2.0 license, allowing free use and modification.
Does TinyStories-656K support vision tasks?
No. The model is purely a language model with no vision capabilities.