Patent Instruct Extended needs about 13.0 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 3.7 GB (Q2_K) to 20.0 GB (F16).
Patent Instruct Extended is a 9.98B-parameter Patent model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 12 quant files, from 3.7 GB (Q2_K) to 20.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.7 GB | 7.4 GB | Tight | Get file → | |
| Q3_K_S | 4.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 4.9 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_L | 5.3 GB | 9.0 GB | Too big | Get file → | |
| IQ4_XS | 5.4 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_S | 5.7 GB | 9.4 GB | Too big | Get file → | |
| Q4_K_M | 6.0 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_S | 6.9 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_M | 7.1 GB | 10.8 GB | Too big | Get file → | |
| Q6_K | 8.2 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 10.6 GB | 14.3 GB | Too big | Get file → | |
| F16 | 20.0 GB | 23.7 GB | Too big | Get file → |
What GPU do you need for Patent Instruct Extended?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q3_K_M (4.9 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (8.2 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (10.6 GB file, about 17.5 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (20.0 GB file, about 26.9 GB in use).
Which Patent Instruct Extended quant should you choose?
Q4_K_M is the usual starting point for Patent Instruct Extended: it balances file size and quality well. Here it is a 6.0 GB file.
The Q8_0 file is 10.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.7 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 Patent Instruct Extended
How much VRAM does Patent Instruct Extended need?
About 13.0 GB at Q4_K_M with an 8K context window. That is the 6.0 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 Patent Instruct Extended on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Patent Instruct Extended GGUF?
It depends on the quant: Q2_K is 3.7 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.9 GB, Q3_K_L is 5.3 GB, IQ4_XS is 5.4 GB, Q4_K_S is 5.7 GB and 6 more.
What context length does Patent Instruct Extended support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.4 GB at 8K and 3.2 GB at 4K.
Where can I download Patent Instruct Extended GGUF?
The files are on Hugging Face in the mradermacher/Patent-Instruct-Extended-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 Patent Instruct Extended 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.