WRT II needs about 6.3 GB of memory at Q4_K_S (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
WRT II is a 8.03B-parameter Llama model in GGUF format, quantized by boapro. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.7 GB (Q4_K_S) to 4.7 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → |
What GPU do you need for WRT II?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K_S (4.7 GB file, about 6.3 GB in use).
Which WRT II quant should you choose?
Q4_K_S (4.7 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 WRT II
How much VRAM does WRT II need?
About 6.3 GB at Q4_K_S with an 8K context window. That is the 4.7 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 WRT II on an 8 GB GPU?
Yes, with Q4_K_S: the 4.7 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of WRT II GGUF?
It depends on the quant: Q4_K_S is 4.7 GB.
What context length does WRT II support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download WRT II GGUF?
The files are on Hugging Face in the boapro/WRT_II repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does WRT II 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.