Sheared LLaMA 1.3B needs about 3.1 GB of memory at Q5_1 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.8 GB (Q4_0) to 2.7 GB (F16).
Sheared LLaMA 1.3B – a pruned, 1.3B‑parameter Llama model
Sheared LLaMA 1.3B is a 1.35‑billion‑parameter model derived from meta‑llama/Llama‑2‑7b‑hf. It was pruned with 0.4B tokens and further pre‑trained on 50B tokens from RedPajama. The model supports a 4096‑token context window and is released under apache‑2.0.
Good at
- Reasoning tasks
- Reading comprehension
- Knowledge‑intensive queries
Limits
- No vision support
- Requires 4096‑token context
- License is apache‑2.0
Best for
- Chatbots with limited GPU memory
- Lightweight research prototypes
- Educational demos
Who it’s for. Developers and researchers needing a small, open‑source Llama variant for quick experimentation or deployment on modest hardware. The model is suitable for those who prefer a balance between performance and resource usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.8 GB | 2.1 GB | Fits | Get file → | |
| Q5_1 | 1.0 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 2.7 GB | Fits | Get file → | |
| F16 | 2.7 GB | 4.0 GB | Fits | Get file → |
For 8 GB VRAM use Q4_0 (0.77 GB file, 2.9 GB memory at 8k context). For 12 GB VRAM use Q5_1 (1.01 GB file, 3.1 GB memory). For 16 GB VRAM use Q8_0 (1.43 GB file, 3.5 GB memory).
What GPU do you need for Sheared LLaMA 1.3B?
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 (1.4 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (2.7 GB file, about 4.8 GB in use).
Which Sheared LLaMA 1.3B quant should you choose?
Q5_1 (1.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 0.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sheared LLaMA 1.3B
How much VRAM does Sheared LLaMA 1.3B need?
About 3.1 GB at Q5_1 with an 8K context window. That is the 1.0 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 Sheared LLaMA 1.3B on an 8 GB GPU?
Yes, with F16: the 2.7 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sheared LLaMA 1.3B GGUF?
It depends on the quant: Q4_0 is 0.8 GB, Q5_1 is 1.0 GB, Q8_0 is 1.4 GB, F16 is 2.7 GB.
What context length does Sheared LLaMA 1.3B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.
Where can I download Sheared LLaMA 1.3B GGUF?
The files are on Hugging Face in the Aryanne/Sheared-LLaMA-1.3B-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 Sheared LLaMA 1.3B 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 Sheared LLaMA 1.3B on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 2.9 GB of VRAM at 8k context, which fits within 8 GB.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.