bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 08:37:17 +08:00
commit 0a15165498
28 changed files with 322 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
.gitattributes vendored Normal file
View File

@@ -0,0 +1,61 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B.imatrix filter=lfs diff=lfs merge=lfs -text

183
README.md Normal file
View File

@@ -0,0 +1,183 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
tags:
- nsfw
- explicit
- roleplay
- unaligned
- dangerous
- ERP
license: gemma
language:
- en
base_model: ReadyArt/Amoral-Fallen-Omega-Gemma3-12B
base_model_relation: quantized
---
## Llamacpp imatrix Quantizations of Amoral-Fallen-Omega-Gemma3-12B by ReadyArt
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5147">b5147</a> for quantization.
Original model: https://huggingface.co/ReadyArt/Amoral-Fallen-Omega-Gemma3-12B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<bos><start_of_turn>user
{system_prompt}
{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Amoral-Fallen-Omega-Gemma3-12B-bf16.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-bf16.gguf) | bf16 | 23.54GB | false | Full BF16 weights. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q8_0.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q8_0.gguf) | Q8_0 | 12.51GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q6_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K_L.gguf) | Q6_K_L | 9.90GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q6_K.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K.gguf) | Q6_K | 9.66GB | false | Very high quality, near perfect, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q5_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_L.gguf) | Q5_K_L | 8.69GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q5_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_M.gguf) | Q5_K_M | 8.44GB | false | High quality, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q5_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_S.gguf) | Q5_K_S | 8.23GB | false | High quality, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q4_1.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_1.gguf) | Q4_1 | 7.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q4_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_L.gguf) | Q4_K_L | 7.54GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q4_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_M.gguf) | Q4_K_M | 7.30GB | false | Good quality, default size for most use cases, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q4_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_S.gguf) | Q4_K_S | 6.94GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q4_0.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_0.gguf) | Q4_0 | 6.91GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ4_NL.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_NL.gguf) | IQ4_NL | 6.89GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q3_K_XL.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_XL.gguf) | Q3_K_XL | 6.72GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ4_XS.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_XS.gguf) | IQ4_XS | 6.55GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q3_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_L.gguf) | Q3_K_L | 6.48GB | false | Lower quality but usable, good for low RAM availability. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q3_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_M.gguf) | Q3_K_M | 6.01GB | false | Low quality. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ3_M.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_M.gguf) | IQ3_M | 5.66GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q3_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_S.gguf) | Q3_K_S | 5.46GB | false | Low quality, not recommended. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ3_XS.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XS.gguf) | IQ3_XS | 5.21GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q2_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K_L.gguf) | Q2_K_L | 5.01GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ3_XXS.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XXS.gguf) | IQ3_XXS | 4.78GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Amoral-Fallen-Omega-Gemma3-12B-Q2_K.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K.gguf) | Q2_K | 4.77GB | false | Very low quality but surprisingly usable. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ2_M.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_M.gguf) | IQ2_M | 4.31GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Amoral-Fallen-Omega-Gemma3-12B-IQ2_S.gguf](https://huggingface.co/bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF/blob/main/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_S.gguf) | IQ2_S | 4.02GB | false | Low quality, uses SOTA techniques to be usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF --include "ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-GGUF --include "ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
</details>
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
Thank you ZeroWw for the inspiration to experiment with embed/output.
Thank you to LM Studio for sponsoring my work.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20a51d012919d82f406ec89a4d7f36745bb27641ffad6d72d80b3cd026d31ef1
size 4310293408

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ca0897d00321cc81e3fee272fe2ae813ddaa4a932d072470edfd6b5dad720d0
size 4020542368

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bec8e488e848a5ca29f55df67c79835543109bb477a92f7ba480615fb6f6b3d5
size 5655522720

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:136f565fd45f62d9c913447d518077a22b28fd742973d0b8d5bd0be0ec085d39
size 5205966240

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b8e8eadd8a3ee00c748c6f6698234f90638f35a23d6c1eb09dd8a34bf927627
size 4784733088

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5af3f05bc7b1bde00bfe48e455fe13f1ae7d57526ce1ca4a97dbd6b9e9af802d
size 6886964640

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f8a975f15f60cf5d30713f01f88a007dfdc2e47ea9065b0af6a5b2f9fd32f1c
size 6550764960

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c5310b2459e7c4c7b0953eabb58ec97c7bc479603f5e518fb0f1ad7f61328f4
size 4768021920

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9608b5f6db461cce1203efcf91432652d58f323524a2a15934b281bdbae67dde
size 5011816768

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:948b3ae66dd6ff50fdc6c5afedc1a87cc9b9d9c5ff3ebe92d483fd18fbcf1da2
size 6479986080

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:984e75da3e6cf2f6980f4b5be83640775ba51cbab49e30fd5efa48624d1225c1
size 6008618400

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13281a1cabca0ab6b44271e58b6e600509e7fd0dbffaf5d329226adecca727d1
size 5458116000

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:130002f39b15538424fbe33f22085b9457d36125f02d99886b2159cfb9a1dccf
size 6723780928

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd1d20bf021355f287ec9ba72639805befa70bb90cf17d12dac13d2cbbc438a8
size 6909083040

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a762e7794845fb3b95b90c3fcf81fdd80003052fd0fd237b608727f4ef955668
size 7559364000

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd4e8daebf32cb6c046a07174be8ffc23460d31b1820709b028e5ee8232ddcca
size 7544373568

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2a2e76be2beb445d3a569ba03661860cd4aef9a4aa3d57aed319e3d1bddc820
size 7300578720

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18bfa195e8b5cc082f0e60c7550dc1292d6910b7270ef68bcea5cafcda7a7aa8
size 6935133600

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91b884abf7e0a9169730502fadb4eae0f26dfb7e4d57dfc47bc3dc4f25579532
size 8688632128

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c232e6223f46b242c6673d3321e210cff1c243a317556d63a93e0fa3c91e5a71
size 8444837280

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f439edb1a661324b7680f6633f670636809e72794dfcc063b289a99277b682d
size 8231763360

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04da1c268a42b040d7efa80e0c2806010493deb91a5182f5563e721083536344
size 9660612000

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c439a74df552e720c883ba911f2b2068ecc313cbfaee6250b722b293c679f501
size 9904406848

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa6970d535a2da16863d5d0f9da45afd0587e057bd487cf139ad54d0e6a223dd
size 12509954368

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8986ea3a8fd30e6dbc9182b464a300dd244accd554864d592584903cc17d0cbf
size 23539666464

3
ReadyArt_Amoral-Fallen-Omega-Gemma3-12B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28488c4759c4e1bac479b1e6c16fc6a96af2a43e2ef0148a4767bc28afd2e557
size 7433114