Tinyllama 2B needs about 2.1 GB of memory at Q4_K (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.8 GB (Q2_K) to 4.1 GB (F16).
Tinyllama 2B is a 2.07B-parameter Kobbletinyv model in GGUF format, quantized by Aculi. Its trained context length is 2K tokens. The repository has 11 quant files, from 0.8 GB (Q2_K) to 4.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q3_K | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_L | 1.1 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K | 1.3 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.0 GB | Fits | Get file → | |
| Q5_K | 1.5 GB | 2.1 GB | Fits | Get file → | |
| Q6_K | 1.7 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 2.2 GB | 2.8 GB | Fits | Get file → | |
| F16 | 4.1 GB | 4.7 GB | Fits | Get file → |
What GPU do you need for Tinyllama 2B?
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 (2.2 GB file, about 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.1 GB file, about 5.0 GB in use).
Which Tinyllama 2B quant should you choose?
Q4_K (1.3 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 Q2_K at 0.8 GB, with the quality trade-offs that come with fewer bits. 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 Tinyllama 2B
How much VRAM does Tinyllama 2B need?
About 2.1 GB at Q4_K with an 8K context window. That is the 1.3 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 Tinyllama 2B on an 8 GB GPU?
Yes, with F16: the 4.1 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Tinyllama 2B GGUF?
It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K is 1.0 GB, Q3_K_L is 1.1 GB, Q4_K_S is 1.2 GB, Q4_K is 1.3 GB and 5 more.
What context length does Tinyllama 2B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.1 GB at 2K.
Where can I download Tinyllama 2B GGUF?
The files are on Hugging Face in the Aculi/Tinyllama-2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.