bartowski/mlabonne_gemma-3-27b-it-abliterated-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/mlabonne_gemma-3-27b-it-abliterated-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-20 03:39:18 +08:00
commit 80c4ecdcbf
32 changed files with 332 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
.gitattributes vendored Normal file
View File

@@ -0,0 +1,65 @@
*.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
mlabonne_gemma-3-27b-it-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-bf16/mlabonne_gemma-3-27b-it-abliterated-bf16-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated-bf16/mlabonne_gemma-3-27b-it-abliterated-bf16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
mlabonne_gemma-3-27b-it-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text
mmproj-mlabonne_gemma-3-27b-it-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text
mmproj-mlabonne_gemma-3-27b-it-abliterated-f32.gguf filter=lfs diff=lfs merge=lfs -text

177
README.md Normal file
View File

@@ -0,0 +1,177 @@
---
quantized_by: bartowski
pipeline_tag: image-text-to-text
license: gemma
base_model: mlabonne/gemma-3-27b-it-abliterated
---
## Llamacpp imatrix Quantizations of gemma-3-27b-it-abliterated by mlabonne
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4896">b4896</a> for quantization.
Original model: https://huggingface.co/mlabonne/gemma-3-27b-it-abliterated
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
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [mmproj-gemma-3-27b-it-abliterated-f32.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mmproj-mlabonne_gemma-3-27b-it-abliterated-f32.gguf) | f32 | 1.69GB | false | F32 format MMPROJ file, required for vision. |
| [mmproj-gemma-3-27b-it-abliterated-f16.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mmproj-mlabonne_gemma-3-27b-it-abliterated-f16.gguf) | f16 | 858MB | false | F16 format MMPROJ file, required for vision. |
| [gemma-3-27b-it-abliterated-bf16.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/tree/main/mlabonne_gemma-3-27b-it-abliterated-bf16) | bf16 | 54.03GB | true | Full BF16 weights. |
| [gemma-3-27b-it-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q8_0.gguf) | Q8_0 | 28.71GB | false | Extremely high quality, generally unneeded but max available quant. |
| [gemma-3-27b-it-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q6_K_L.gguf) | Q6_K_L | 22.51GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [gemma-3-27b-it-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q6_K.gguf) | Q6_K | 22.17GB | false | Very high quality, near perfect, *recommended*. |
| [gemma-3-27b-it-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q5_K_L.gguf) | Q5_K_L | 19.61GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [gemma-3-27b-it-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q5_K_M.gguf) | Q5_K_M | 19.27GB | false | High quality, *recommended*. |
| [gemma-3-27b-it-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q5_K_S.gguf) | Q5_K_S | 18.77GB | false | High quality, *recommended*. |
| [gemma-3-27b-it-abliterated-Q4_1.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q4_1.gguf) | Q4_1 | 17.17GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [gemma-3-27b-it-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q4_K_L.gguf) | Q4_K_L | 16.89GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [gemma-3-27b-it-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q4_K_M.gguf) | Q4_K_M | 16.55GB | false | Good quality, default size for most use cases, *recommended*. |
| [gemma-3-27b-it-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q4_K_S.gguf) | Q4_K_S | 15.67GB | false | Slightly lower quality with more space savings, *recommended*. |
| [gemma-3-27b-it-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q4_0.gguf) | Q4_0 | 15.62GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [gemma-3-27b-it-abliterated-IQ4_NL.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ4_NL.gguf) | IQ4_NL | 15.57GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [gemma-3-27b-it-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 14.88GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [gemma-3-27b-it-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ4_XS.gguf) | IQ4_XS | 14.77GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [gemma-3-27b-it-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q3_K_L.gguf) | Q3_K_L | 14.54GB | false | Lower quality but usable, good for low RAM availability. |
| [gemma-3-27b-it-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q3_K_M.gguf) | Q3_K_M | 13.44GB | false | Low quality. |
| [gemma-3-27b-it-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ3_M.gguf) | IQ3_M | 12.55GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [gemma-3-27b-it-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q3_K_S.gguf) | Q3_K_S | 12.17GB | false | Low quality, not recommended. |
| [gemma-3-27b-it-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ3_XS.gguf) | IQ3_XS | 11.56GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [gemma-3-27b-it-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q2_K_L.gguf) | Q2_K_L | 10.85GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [gemma-3-27b-it-abliterated-IQ3_XXS.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ3_XXS.gguf) | IQ3_XXS | 10.72GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [gemma-3-27b-it-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-Q2_K.gguf) | Q2_K | 10.50GB | false | Very low quality but surprisingly usable. |
| [gemma-3-27b-it-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ2_M.gguf) | IQ2_M | 9.49GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [gemma-3-27b-it-abliterated-IQ2_S.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ2_S.gguf) | IQ2_S | 8.78GB | false | Low quality, uses SOTA techniques to be usable. |
| [gemma-3-27b-it-abliterated-IQ2_XS.gguf](https://huggingface.co/bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF/blob/main/mlabonne_gemma-3-27b-it-abliterated-IQ2_XS.gguf) | IQ2_XS | 8.44GB | 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/mlabonne_gemma-3-27b-it-abliterated-GGUF --include "mlabonne_gemma-3-27b-it-abliterated-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/mlabonne_gemma-3-27b-it-abliterated-GGUF --include "mlabonne_gemma-3-27b-it-abliterated-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (mlabonne_gemma-3-27b-it-abliterated-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.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</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
mlabonne_gemma-3-27b-it-abliterated-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4732f17dfa88aac103ab93838836616b53c849314a0f32cc2fe0bc3bcde3669d
size 9493073280

3
mlabonne_gemma-3-27b-it-abliterated-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09022f4403c19ea96de6a73f5cd507264a613f9f4a203f04331c7521807f79cd
size 8782409088

3
mlabonne_gemma-3-27b-it-abliterated-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1750f3288909c85a085dc5053fb18b0a496e9a6bae01427ada4ad33d88060499
size 8438904192

3
mlabonne_gemma-3-27b-it-abliterated-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f28454ea219713ea1e3fb5f1707ba05bc2943ab5b076de35398e445d64289a3
size 12547074048

3
mlabonne_gemma-3-27b-it-abliterated-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5512fffe76eaa09d09137c0b5f3da9ef293762ce5fd2c36ae9433f969729c6a1
size 11562233856

3
mlabonne_gemma-3-27b-it-abliterated-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c3376cf8ebf271c34b01a246b4fbe19fbbc39636accbd82efcd01d618a9fd7e5
size 10716478848

3
mlabonne_gemma-3-27b-it-abliterated-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ae669c2134a4bbfaafd181ebe2be4bd10c639e2b526745d12fe343616b2fe302
size 15567396864

3
mlabonne_gemma-3-27b-it-abliterated-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:546b0db7ca7b7333033df006afcbef5894db8b551c95e63a369de49b9080dae2
size 14767448064

3
mlabonne_gemma-3-27b-it-abliterated-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:928089d6517282a950741d2a129519bfec8ee8e197a896ef4476b4d9a39eb920
size 10503720960

3
mlabonne_gemma-3-27b-it-abliterated-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8005bfaf84ea63425dc57b5565fcfa1c54d5cd19de066ccf10b37a9e26f8cebd
size 10845115776

3
mlabonne_gemma-3-27b-it-abliterated-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce0e0942b80e02d40dc1ee4caaf82dfd0b932ddc0a97c6c86d6e69954cb7a65d
size 14543462400

3
mlabonne_gemma-3-27b-it-abliterated-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5974ff673a0e49bea2dc4d0c59a8404bb6d67c3c3f668df2c01ab102eb8d4db
size 13437640704

3
mlabonne_gemma-3-27b-it-abliterated-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b667afaedee713406c363ec616621f3ce6f52cadf7913ab80e87e34d7eaa48f5
size 12167614464

3
mlabonne_gemma-3-27b-it-abliterated-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2a73577208eae3bb65dceb192558655464fd431c9b82cb2dc2b15792b4fe200
size 14884857216

3
mlabonne_gemma-3-27b-it-abliterated-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d47047ff6fabb02e8aa8bea1d3fd32a551382016bd7d91f45f74615ada670a21
size 15617974272

3
mlabonne_gemma-3-27b-it-abliterated-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cbf3244a72d2f1ffad2c8065c9e14ca0feaf5a6a160874a547843a118cc7d505
size 17167294464

3
mlabonne_gemma-3-27b-it-abliterated-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4514951114aa70ae03853688fbbeef87e12d34ceb6fa66399fe518edc0f1017b
size 16888083840

3
mlabonne_gemma-3-27b-it-abliterated-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d7afea4b1889c113f4a8ec1855d23bee71b3e3bedcb1fad84f9c9ffcdfe07d0
size 16546689024

3
mlabonne_gemma-3-27b-it-abliterated-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a748af5b9220ada9cd789af06018409ffc4f4a99c97d241047b2024746a5b9bd
size 15674056704

3
mlabonne_gemma-3-27b-it-abliterated-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5698c3694291783a0cf685592d4c7338bba6e2de608394705b93ff5f4562c112
size 19613070720

3
mlabonne_gemma-3-27b-it-abliterated-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66e3dff3a5073e6e8cdbf585253df1b15a006607c870534be44ef1b45af0043a
size 19271675904

3
mlabonne_gemma-3-27b-it-abliterated-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b7a7f9da618e88637a3e505b3e897b5e0ca811bd76424b94bc6984f3cc9438b
size 18767192064

3
mlabonne_gemma-3-27b-it-abliterated-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a06b9e6d6efe4b48fbd6f6bb9a12165a76a6c4b6f122ada048ac81655e4dfcf1
size 22166974464

3
mlabonne_gemma-3-27b-it-abliterated-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67e87a8708813b7411702289b6dd3ca26b59c7a73991e18a503e91d5935b5a64
size 22508369280

3
mlabonne_gemma-3-27b-it-abliterated-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8db6987e3bd6e5f7c57fe414eebe8ad38302a96792ce2e67535e17537df3c47
size 28707972480

3
mlabonne_gemma-3-27b-it-abliterated-bf16/mlabonne_gemma-3-27b-it-abliterated-bf16-00001-of-00002.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6e07fcb8d1ae03df5d21daa711f84fb37aec924c67098ffea072abb0ee0035a5
size 39988660512

3
mlabonne_gemma-3-27b-it-abliterated-bf16/mlabonne_gemma-3-27b-it-abliterated-bf16-00002-of-00002.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10b519e89845d42827eeb99739f330cdc5b29c85d089726f85b2b670bdf606f5
size 14039304192

3
mlabonne_gemma-3-27b-it-abliterated.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:db2f3f8cc10f32577072234f87a8e0925368302508efc17eb63b398ac695d93a
size 13029464

3
mmproj-mlabonne_gemma-3-27b-it-abliterated-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54cb61c842fe49ac3c89bc1a614a2778163eb49f3dec2b90ff688b4c0392cb48
size 857739168

3
mmproj-mlabonne_gemma-3-27b-it-abliterated-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a8b849e20a59ec2b255d308ec6488a3a44fa6e06b2a0514c59eab983930c0b27
size 1692266400