quant type needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.0 GB (IQ1_S) to 0.0 GB (Q8_0).
quant type is a Quant model in GGUF format, quantized by gguf-org. The repository has 24 quant files, from 0.0 GB (IQ1_S) to 0.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ1_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| TQ1_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_XXS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| TQ2_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q2_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q2_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_XXS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_NL | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → |
What GPU do you need for quant type?
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 (0.0 GB file, about 0.5 GB in use).
Which quant type quant should you choose?
Q4_K_M is the usual starting point for quant type: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 0.0 GB, about 1.9 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 IQ1_S at 0.0 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 quant type
How much VRAM does quant type need?
About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 quant type on an 8 GB GPU?
Yes, with Q8_0: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of quant type GGUF?
It depends on the quant: IQ1_S is 0.0 GB, IQ1_M is 0.0 GB, TQ1_0 is 0.0 GB, IQ2_XXS is 0.0 GB, IQ2_XS is 0.0 GB, TQ2_0 is 0.0 GB and 18 more.
Where can I download quant type GGUF?
The files are on Hugging Face in the gguf-org/quant-type repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does quant type 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.