tiny1m needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.0 GB (IQ3_S) to 0.0 GB (F32).
Tiny 1M‑parameter Llama model for lightweight inference
TinyStories Llama2 1M (tiny1m) is a 1M‑parameter Llama model optimized for ultra‑lightweight inference. It is available in multiple GGUF quantizations and a Hugging Face safetensors format. The model is licensed under MIT and supports 256‑token context.
Good at
- Fast inference on low‑memory devices
- Rapid validation of inference engines
- Debugging quantization kernels
Limits
- 256‑token context only
- No vision or multimodal support
- Requires GPU or CPU with enough RAM for chosen quant
Best for
- Embedded LLM demos
- Unit testing of llama.cpp loaders
- Educational projects on model size
Who it’s for. Developers building or testing lightweight LLM inference pipelines. Researchers needing a minimal model for rapid prototyping. Educators demonstrating LLM concepts without large hardware requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_XXS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_NL | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q2_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| TQ1_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| TQ2_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_L | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| BF16 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| F16 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| F32 | 0.0 GB | 0.5 GB | Fits | Get file → |
For 8 GB VRAM, use IQ3_S or Q4_0; both use about 0.5 GB memory at 8 k context. For 4 GB VRAM, IQ3_XXS or Q4_XS are suitable. For CPU‑only runs with limited RAM, Q2_K or Q4_NL provide the lowest memory footprint.
What GPU do you need for tiny1m?
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 (0.0 GB file, about 0.5 GB in use).
Which tiny1m quant should you choose?
Q4_K_M is the usual starting point for tiny1m: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 0.0 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ3_S at 0.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tiny1m
How much VRAM does tiny1m need?
About 0.5 GB at Q4_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 tiny1m on an 8 GB GPU?
Yes, with F32: 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 tiny1m GGUF?
It depends on the quant: IQ3_S is 0.0 GB, IQ3_XXS is 0.0 GB, IQ4_NL is 0.0 GB, IQ4_XS is 0.0 GB, Q2_K is 0.0 GB, Q4_0 is 0.0 GB and 15 more.
What context length does tiny1m support?
The GGUF header lists a trained context length of 256 tokens (256). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.0 GB at 256.
Where can I download tiny1m GGUF?
The files are on Hugging Face in the shibatch/tiny1m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tiny1m 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.
Can I run tiny1m on 4 GB VRAM?
Yes, quantizations like IQ3_XXS or Q4_XS use approximately 0.5 GB memory at 8 k context, fitting within 4 GB VRAM.
Does tiny1m support vision tasks?
No, the model is purely text and has no vision or multimodal capabilities.