---
datasets:
- tiiuae/falcon-refinedweb
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About

weighted/imatrix quants of https://huggingface.co/tiiuae/falcon-40b-instruct

<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF
## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.

## Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 15.1 |  |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 16.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 17.0 | fast, lower quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.9 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 22.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 26.1 | fast, medium quality |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 29.6 |  |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.2 |  |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |


Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

## Thanks

I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

<!-- end -->