commit b93df9b3e6c8e113635bf5b69ea58a274587b56f Author: ModelHub XC Date: Wed Jul 22 12:00:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e830078 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-bf16.gguf filter=lfs diff=lfs merge=lfs -text +p-e-w_Qwen3-4B-Instruct-2507-heretic-imatrix.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..b14bef5 --- /dev/null +++ b/README.md @@ -0,0 +1,179 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: p-e-w/Qwen3-4B-Instruct-2507-heretic +license: apache-2.0 +tags: +- heretic +- uncensored +- decensored +- abliterated +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +--- + +## Llamacpp imatrix Quantizations of Qwen3-4B-Instruct-2507-heretic by p-e-w + +Using llama.cpp release b7049 for quantization. + +Original model: https://huggingface.co/p-e-w/Qwen3-4B-Instruct-2507-heretic + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` +<|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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Qwen3-4B-Instruct-2507-heretic-bf16.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. | +| [Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. | +| [Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. | +| [Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. | +| [Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf](https://huggingface.co/bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF/blob/main/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf) | IQ2_M | 1.51GB | 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/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF --include "p-e-w_Qwen3-4B-Instruct-2507-heretic-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/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF --include "p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (p-e-w_Qwen3-4B-Instruct-2507-heretic-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf new file mode 100644 index 0000000..3ee440a --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e36a40601b35fb543397b6448f219ecd74c286584a09f6367589f8fe3235cf +size 1512982464 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf new file mode 100644 index 0000000..39d8460 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c46c7eab6aaf423d072d14aef842db49c9c362d0452442293a75c812a4ef6f5 +size 1962894784 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf new file mode 100644 index 0000000..4e97417 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6391d19e3ccf632953b058620b2129c2a0e8353b6122f5254aadc9cf7fb595 +size 1814373824 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf new file mode 100644 index 0000000..8a82221 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35728751e3a6732e2a3588db91fdc3d060733654180a63a563064e1106b2cc22 +size 1670186944 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf new file mode 100644 index 0000000..fe610b9 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471c0e85daa66c748d2a07d742a2bb83e5841ddab2d02b961fd275c33e954a65 +size 2381342144 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf new file mode 100644 index 0000000..45a7db0 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ba6afc1790631cc5b6e6b1412011ef0cdb78171922e2932d04e861689280a7 +size 2270750144 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf new file mode 100644 index 0000000..4b8338b --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6161832af29bc7138542d74a84a0e220e13dbeb36e27ce9deed594f04f75a98c +size 1669498304 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf new file mode 100644 index 0000000..4117afd --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae5f3e2a68b78abb75f5520bf98eb9cf31877950d5e855b21d3850775f4457c +size 1763698624 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf new file mode 100644 index 0000000..bc026e0 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e4b7cc5244f15f9083be8bd94a50c21481d75bab38b848a13f2f53a2fa5eaf +size 2239784384 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf new file mode 100644 index 0000000..2e1c976 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841e704f85f318f0cf361cb6a3cd12853f0ec5d2eecc34b4eb95547f916db304 +size 2075616704 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf new file mode 100644 index 0000000..b497c24 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9559d48fad8195d75dd0d9e2474bab8bd9be2aecb8002300e5f910394207cea5 +size 1886995904 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf new file mode 100644 index 0000000..c0a1ce5 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c785c7803bce3f5275c8d45563ce02f23dcac404c00667456c096687aceca561 +size 2333984704 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf new file mode 100644 index 0000000..1c9a982 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e827b60180825f16f4921a7bd62ae0b5b9d04433a4928685fc82ff558cc839 +size 2375771584 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf new file mode 100644 index 0000000..75b278d --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb18ba2e43641c06fa0ed13fe959e0704f010e4d76ce30d7fd745776f0a72b46 +size 2596627904 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf new file mode 100644 index 0000000..95b56a6 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ead716d0dbfeab21f55a740639f21584ee5a5f5c76706b9585c7f4454eb84876 +size 2591479744 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf new file mode 100644 index 0000000..e1c16e3 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d7fcd11d36495fa340f91b514ae3a47f5da21cf27c158d620d736e3bb35a61 +size 2497279424 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf new file mode 100644 index 0000000..9760332 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea7a24f56a56673fc5201a5c2aa4d4417f718e6ea64ecc74725ab9d33b28fca +size 2383308224 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf new file mode 100644 index 0000000..b33b179 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5cdec387da647220b9b8aee13add64d2debb4567722569aedb5f89f124843e +size 2983712704 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf new file mode 100644 index 0000000..3ed1862 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b31a65fbaafaf54830e94295cd339cb9b00a215bc584280607e794d32b6975a +size 2889512384 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf new file mode 100644 index 0000000..eda666b --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50462f2886b51d04624329741544cca014cb684472d362ad7d1b04703c35e9a6 +size 2823710144 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf new file mode 100644 index 0000000..0cfcb40 --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f4fd5b191fcca42e5fc45ec1dcf2f6ab6e6646c557b2efec63dcfcc56e5ee3 +size 3306259904 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf new file mode 100644 index 0000000..251633f --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd4265204694f9adb76ccff7b07a541b74dfa53eff7d0f3aac65ad194473613 +size 3400460224 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf new file mode 100644 index 0000000..d37a2ae --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b990e208f13616ec08d6e9eb1a5ac785582f0e8a48ee1e22238efb3fe4e986e +size 4280403904 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-bf16.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-bf16.gguf new file mode 100644 index 0000000..c694adb --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582bb56e63b967d695a74626fa5ad260953935ee2b80e3dbb75cbb3e37a2bb3c +size 8051283584 diff --git a/p-e-w_Qwen3-4B-Instruct-2507-heretic-imatrix.gguf b/p-e-w_Qwen3-4B-Instruct-2507-heretic-imatrix.gguf new file mode 100644 index 0000000..3451c7e --- /dev/null +++ b/p-e-w_Qwen3-4B-Instruct-2507-heretic-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9808c7178a992e52b2024023025a8390b4496b5793d69ec25e85727ba41c819 +size 3872640