model needs about 2.7 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 1.6 GB (IQ1_S) to 9.7 GB (Q3_K_M).
model is a 20.4B-parameter Model model in GGUF format, quantized by Anton-Ding. The repository has 8 quant files, from 1.6 GB (IQ1_S) to 9.7 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.6 GB | 2.3 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 9.7 GB | 11.3 GB | Too big | Get file → | |
| Q3_K_M | 9.7 GB | 11.3 GB | Too big | Get file → |
What GPU do you need for model?
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 Q5_K_M (2.4 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (9.7 GB file, about 11.3 GB in use).
Which model quant should you choose?
Q4_K_M is the usual starting point for model: it balances file size and quality well. Here it is a 2.0 GB file.
If memory is tight, the smallest file is IQ1_S at 1.6 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 model
How much VRAM does model need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 2.0 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 model on an 8 GB GPU?
Yes, with Q4_K_M: the 4.4 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of model GGUF?
It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, Q4_K_M is 2.0 GB, IQ2_XS is 2.2 GB, Q5_K_M is 2.4 GB, Q4_K_M is 4.4 GB and 2 more.
Where can I download model GGUF?
The files are on Hugging Face in the Anton-Ding/model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.