---
base_model: spow12/ChatWaifu_72B_v2.2
datasets:
- roleplay4fun/aesir-v1.1
- kalomaze/Opus_Instruct_3k
- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
- Nopm/Opus_WritingStruct
- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
- anthracite-org/stheno-filtered-v1.1
- SicariusSicariiStuff/Bluemoon_Top50MB_Sorted_Fixed
- Aratako/Magpie-Tanuki-8B-97k
- Aratako_Synthetic_JP_EN_Coding_Dataset_801k
- Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted
- Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted
- Aratako_Synthetic_JP_EN_Translation_Dataset_Magpie_Nemotron
- Aratako_Rosebleu_1on1_Dialogues_RP
- Team-ACE/ToolACE
- SkunkworksAI/reasoning-0.01
- HuggingFaceTB/smoltalk
- microsoft_orca_agentinstruct_1M_v1
- Aratako/Magpie-Tanuki-8B-97k
language:
- en
- ja
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
- nsfw
- Visual novel
- roleplay
- mergekit
- merge
---
## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
static quants of https://huggingface.co/spow12/ChatWaifu_72B_v2.2

<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-i1-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/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q2_K.gguf) | Q2_K | 29.9 |  |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q3_K_S.gguf) | Q3_K_S | 34.6 |  |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q3_K_L.gguf) | Q3_K_L | 39.6 |  |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.IQ4_XS.gguf) | IQ4_XS | 40.3 |  |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 |  |
| [PART 1](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 |  |
| [PART 1](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ChatWaifu_72B_v2.2-GGUF/resolve/main/ChatWaifu_72B_v2.2.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |

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

## FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

## 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 -->