tinyllamas BE needs about 0.5 GB of memory at Q4_0 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB to 0.1 GB.
tinyllamas BE – a 24‑million‑parameter Llama 2 model
tinyllamas BE is a 0.0244‑billion‑parameter Llama 2 architecture model trained on TinyStories. It is released under the MIT license and is designed for use with llama2.c on Big‑Endian systems.
Good at
- Small footprint inference
- Fast token generation
- Compatible with llama2.c
Limits
- No vision support
- Limited context length (8k tokens)
- No mixture of experts
Best for
- Embedded inference
- Rapid prototyping
- Low‑resource deployments
Who it’s for. Developers needing a lightweight Llama 2 model for local inference on modest hardware. The model is suitable for projects that require quick turnaround and minimal storage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_0 quantization (0.02 GB file, 0.5 GB memory at 8k context) is ideal. If more memory is available, the Q8_0 quant (0.03 GB file, 0.5 GB memory) offers higher precision. The unknown quant (0.1 GB file, 0.6 GB memory) can be used when precision is not critical.
What GPU do you need for tinyllamas BE?
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 the main file (0.1 GB file, about 0.6 GB in use).
Which tinyllamas BE quant should you choose?
Q4_0 (0.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tinyllamas BE
How much VRAM does tinyllamas BE need?
About 0.5 GB at Q4_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 tinyllamas BE on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of tinyllamas BE GGUF?
It depends on the quant: file is 0.0 GB, Q4_0 is 0.0 GB, Q8_0 is 0.0 GB, file is 0.1 GB.
Where can I download tinyllamas BE GGUF?
The files are on Hugging Face in the taronaeo/tinyllamas-BE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tinyllamas BE 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 tinyllamas BE on 8 GB VRAM?
Yes, the Q4_0 quant uses about 0.5 GB of VRAM at 8k context, well within an 8 GB budget.
Does this model support vision tasks?
No, tinyllamas BE is a text‑only model and does not include vision capabilities.
What license does it use?
The model is released under the MIT license, allowing free use and modification.