harrier needs about 0.8 GB of memory at Q4_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q4_0) to 0.3 GB (Q8_0).
harrier is a 268M-parameter Harrier model in GGUF format, quantized by appvoid. The repository has 2 quant files, from 0.2 GB (Q4_0) to 0.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → |
What GPU do you need for harrier?
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 Q8_0 (0.3 GB file, about 0.8 GB in use).
Which harrier quant should you choose?
Q4_0 (0.2 GB) is the middle option in this repository. 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 harrier
How much VRAM does harrier need?
About 0.8 GB at Q4_0 with an 8K context window. That is the 0.2 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 harrier on an 8 GB GPU?
Yes, with Q8_0: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of harrier GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q8_0 is 0.3 GB.
Where can I download harrier GGUF?
The files are on Hugging Face in the appvoid/harrier-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 harrier 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.