commit a77881ae5f45517345cea5d200ad6c42b1825d56 Author: ModelHub XC Date: Fri Aug 28 05:55:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9565bb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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_Qwen3-0.6B-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-0.6B-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e8480f7 --- /dev/null +++ b/README.md @@ -0,0 +1,171 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: mlabonne/Qwen3-0.6B-abliterated +tags: [] +--- + +## Llamacpp imatrix Quantizations of Qwen3-0.6B-abliterated by mlabonne + +Using llama.cpp release b5228 for quantization. + +Original model: https://huggingface.co/mlabonne/Qwen3-0.6B-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 + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Qwen3-0.6B-abliterated-bf16.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-bf16.gguf) | bf16 | 1.20GB | false | Full BF16 weights. | +| [Qwen3-0.6B-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q8_0.gguf) | Q8_0 | 0.64GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Qwen3-0.6B-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q6_K_L.gguf) | Q6_K_L | 0.53GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Qwen3-0.6B-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q6_K.gguf) | Q6_K | 0.50GB | false | Very high quality, near perfect, *recommended*. | +| [Qwen3-0.6B-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q5_K_L.gguf) | Q5_K_L | 0.48GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Qwen3-0.6B-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q5_K_M.gguf) | Q5_K_M | 0.44GB | false | High quality, *recommended*. | +| [Qwen3-0.6B-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q5_K_S.gguf) | Q5_K_S | 0.44GB | false | High quality, *recommended*. | +| [Qwen3-0.6B-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q4_K_L.gguf) | Q4_K_L | 0.43GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Qwen3-0.6B-abliterated-Q4_1.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q4_1.gguf) | Q4_1 | 0.41GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Qwen3-0.6B-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 0.41GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Qwen3-0.6B-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf) | Q4_K_M | 0.40GB | false | Good quality, default size for most use cases, *recommended*. | +| [Qwen3-0.6B-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q4_K_S.gguf) | Q4_K_S | 0.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Qwen3-0.6B-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q4_0.gguf) | Q4_0 | 0.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Qwen3-0.6B-abliterated-IQ4_NL.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ4_NL.gguf) | IQ4_NL | 0.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Qwen3-0.6B-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ4_XS.gguf) | IQ4_XS | 0.37GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen3-0.6B-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q3_K_L.gguf) | Q3_K_L | 0.37GB | false | Lower quality but usable, good for low RAM availability. | +| [Qwen3-0.6B-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q3_K_M.gguf) | Q3_K_M | 0.35GB | false | Low quality. | +| [Qwen3-0.6B-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ3_M.gguf) | IQ3_M | 0.34GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen3-0.6B-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q2_K_L.gguf) | Q2_K_L | 0.33GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Qwen3-0.6B-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q3_K_S.gguf) | Q3_K_S | 0.32GB | false | Low quality, not recommended. | +| [Qwen3-0.6B-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ3_XS.gguf) | IQ3_XS | 0.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen3-0.6B-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-Q2_K.gguf) | Q2_K | 0.30GB | false | Very low quality but surprisingly usable. | +| [Qwen3-0.6B-abliterated-IQ3_XXS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ3_XXS.gguf) | IQ3_XXS | 0.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen3-0.6B-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF/blob/main/mlabonne_Qwen3-0.6B-abliterated-IQ2_M.gguf) | IQ2_M | 0.26GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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 + +
+ Click to view download instructions + +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_Qwen3-0.6B-abliterated-GGUF --include "mlabonne_Qwen3-0.6B-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_Qwen3-0.6B-abliterated-GGUF --include "mlabonne_Qwen3-0.6B-abliterated-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (mlabonne_Qwen3-0.6B-abliterated-Q8_0) or download them all in place (./) + +
+ +## 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. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| 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 + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +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. + +
+ +## 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 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ2_M.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ2_M.gguf new file mode 100644 index 0000000..caa6890 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9ca775b7af71deaf76f92e9dec3e23c2ef07012981639e2db9e51b05797153 +size 264908736 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ3_M.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ3_M.gguf new file mode 100644 index 0000000..e6fb133 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fadccdb165db1306a9148e1fa4c9df76073b52b4084710722fb8a7cb9cc8fff +size 336026560 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ3_XS.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ3_XS.gguf new file mode 100644 index 0000000..0f2ee2c --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774ae9e0994ebbbe6fcd934ca4d7561c8c4ca3c9a81f7449aabde8af161231ba +size 312753088 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ3_XXS.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ3_XXS.gguf new file mode 100644 index 0000000..8096cfc --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e46ac86e3d52c1fa9f5ab9ecd53836b826c715186c37b3ebca32a5658f6726c +size 279015360 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ4_NL.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ4_NL.gguf new file mode 100644 index 0000000..bd669d6 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba4e6ee8a33d03c4a797bd00f97e8dc62f2c3b615fd30cdbdaa566327ec4a0a +size 381565888 diff --git a/mlabonne_Qwen3-0.6B-abliterated-IQ4_XS.gguf b/mlabonne_Qwen3-0.6B-abliterated-IQ4_XS.gguf new file mode 100644 index 0000000..3ede877 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55942da4e34ad01288271db232bcfdd14fa39b1994cbba59be895f9444ec3c5a +size 367803328 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q2_K.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q2_K.gguf new file mode 100644 index 0000000..af5b4ab --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f3272124ef7ec4a035585f2b72aab5ddc7d5c237128a7283e492fd954fded1 +size 296238016 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q2_K_L.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q2_K_L.gguf new file mode 100644 index 0000000..2477a18 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d443875c11ec7d5cb1a352eee61979394c7247a02824779a95637ef3ece8cfa +size 333918144 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q3_K_L.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_L.gguf new file mode 100644 index 0000000..7d99b02 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f45aa4e516efbc2433da17f3ce5964be87ff51b653aba2fe5372faabf7937b4 +size 368491456 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q3_K_M.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_M.gguf new file mode 100644 index 0000000..8a3fb1c --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae8b2c57deacfcef5709efec06834fb8634a0f3610780f6281ee7347c4336cb +size 347126720 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q3_K_S.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_S.gguf new file mode 100644 index 0000000..486f1f2 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee20f437fc509eaa2fe7e8045d568e584a1785cbcd88fa3534d89bc968f342de +size 323075008 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q3_K_XL.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_XL.gguf new file mode 100644 index 0000000..9bc4b6c --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4b410c22e0943e20dd08d1410d7d47935346904cfd6c72efbbb07d9cee291c +size 406171584 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q4_0.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q4_0.gguf new file mode 100644 index 0000000..0637bd0 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e410f56339b82b20a3ea2e73a04f43d4e247c9256fc11a9b4d835bf3192d606 +size 382155712 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q4_1.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q4_1.gguf new file mode 100644 index 0000000..e3c3f01 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f6ba6117a82165cc3b2f8c6bceaf7f7df6901c9aa0a549300fe88f234e0323 +size 409091008 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q4_K_L.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_L.gguf new file mode 100644 index 0000000..1210109 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c49b9005d34859e06eb7f8c80e2e93cea1ec14f381b2e4eb2792f80ab02a8a +size 434384832 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf new file mode 100644 index 0000000..574d010 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cacbf2f07c675bee319a210a22244ad4a8ba86f79daf67b7ede1da14ce8e6b99 +size 396704704 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q4_K_S.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_S.gguf new file mode 100644 index 0000000..99a25a7 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34bbb100d6af518da14ff07dea3ba57aae447eb89edab610a0b8f56faf1e78ed +size 383269824 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q5_K_L.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_L.gguf new file mode 100644 index 0000000..451665d --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4bf1937a2c1d7fc30650b3de41af9919d80017c1b269549023abfaeb9154229 +size 482095040 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q5_K_M.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_M.gguf new file mode 100644 index 0000000..7b64b73 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e46a7538eab1e9aa24842d31a84a7a965f66a14dc41e8b9234f04cbf49d3547b +size 444414912 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q5_K_S.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_S.gguf new file mode 100644 index 0000000..2eb3482 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95918db61d6e2f0cebf7e68816b373cba65b1a1bb6aa0650467b6fa96cab15b8 +size 436616128 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q6_K.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q6_K.gguf new file mode 100644 index 0000000..1d57a27 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c2b454e12a3c8725828441dbdf7af29b8cde718290b23de1cc020e4b3df3de +size 495107008 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q6_K_L.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q6_K_L.gguf new file mode 100644 index 0000000..d636f96 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05596403d7858b7520225c855fce194681877432f46bf3e3632acc204ec2f178 +size 532787136 diff --git a/mlabonne_Qwen3-0.6B-abliterated-Q8_0.gguf b/mlabonne_Qwen3-0.6B-abliterated-Q8_0.gguf new file mode 100644 index 0000000..e9aad9c --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2429be2938f64f2dcb860e25cdb0bb9915222ca9346a68be8611af6a2713b4eb +size 639446976 diff --git a/mlabonne_Qwen3-0.6B-abliterated-bf16.gguf b/mlabonne_Qwen3-0.6B-abliterated-bf16.gguf new file mode 100644 index 0000000..13a49be --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556b993fb6da5e4e12e2a0696e41fe0f07cb45416f4fc0a6a283f23a88e57a55 +size 1198182048 diff --git a/mlabonne_Qwen3-0.6B-abliterated.imatrix b/mlabonne_Qwen3-0.6B-abliterated.imatrix new file mode 100644 index 0000000..e167ce9 --- /dev/null +++ b/mlabonne_Qwen3-0.6B-abliterated.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ed1136753e3e0ece8308190ed09ba6d8c3e225b542c80a86b779e74bb60cd7 +size 1153382