commit 6b0f71611e19582f0986cac111e2480932004f3a Author: ModelHub XC Date: Mon Apr 20 15:24:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a302e00 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-32B-Thinking-abliterated-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.IQ4_XS.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.IQ4_XS.gguf new file mode 100644 index 0000000..ad438ad --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bce58f1274e52916da59de46dc01cb075480c0e5b82bab016ca0910ed659b4c +size 17854336864 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q2_K.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q2_K.gguf new file mode 100644 index 0000000..d6ec80e --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23b95c09638750b51144701fad6c54c38b0f3e91a6018df17f63999e7999d89 +size 12344653664 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_L.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_L.gguf new file mode 100644 index 0000000..ffa5059 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f544d9062a418916f4dd7f67e91d4a5b0a034ecf6d30c1786aa194fda122175 +size 17330996064 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_M.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_M.gguf new file mode 100644 index 0000000..2c65b60 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956bc608214a8a0d3744ac5e6b19f7aa188cc06fb4f7ff24ec890196ffa53f89 +size 15971779424 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_S.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_S.gguf new file mode 100644 index 0000000..3e67b81 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1e1c2fe261f1b44d836541fa4c9b6ff6e661ad5c49c559bad460749431badc +size 14389740384 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_M.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_M.gguf new file mode 100644 index 0000000..bbc5f18 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c2dec1ffdf4310c1a5a100e81eab6cedd3bcce915542fc64f186db6319755d +size 19762151264 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_S.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_S.gguf new file mode 100644 index 0000000..e984406 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15edc26e5af72168a41f75e2a828483a32b6e706b2086c9f14a7eecf367defc2 +size 18771246944 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_M.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_M.gguf new file mode 100644 index 0000000..7fd132b --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fa9703788fbfb808cb8da053a8ed23f1af8aa999ff2dde6c2d17518284acbb +size 23214833504 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_S.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_S.gguf new file mode 100644 index 0000000..8b0459a --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef476c4b1cabb950c46906c984f94aa881a3c2598674520df2885a1fbff73bb +size 22635495264 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q6_K.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q6_K.gguf new file mode 100644 index 0000000..d5aa9c3 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ceca2216a77f2125d59f83068d210a0b6f53b2ba3afbb53018dd0c28be37c2e +size 26883308384 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.Q8_0.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.Q8_0.gguf new file mode 100644 index 0000000..8cb1f26 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e8753ac31639a887c710f860843725ccb34ed409faada29a3f222feb81be0d +size 34817721184 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-Q8_0.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-Q8_0.gguf new file mode 100644 index 0000000..7610fde --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8552a892b4ecedf5070a49ab21f6eb35a246069c8a5496e0f341c7fe886611 +size 772360672 diff --git a/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-f16.gguf b/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-f16.gguf new file mode 100644 index 0000000..6390c43 --- /dev/null +++ b/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2882fc2251d581566813900c3a86af6452e383142b57ba8182f82c7b9f9316aa +size 1196795488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8811606 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: prithivMLmods/Qwen3-VL-32B-Thinking-abliterated-v1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- abliterated +- v1.0 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/Qwen3-VL-32B-Thinking-abliterated-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-32B-Thinking-abliterated-v1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q2_K.gguf) | Q2_K | 12.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_S.gguf) | Q3_K_S | 14.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_M.gguf) | Q3_K_M | 16.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q3_K_L.gguf) | Q3_K_L | 17.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.IQ4_XS.gguf) | IQ4_XS | 18.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_S.gguf) | Q4_K_S | 18.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q4_K_M.gguf) | Q4_K_M | 19.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_S.gguf) | Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q5_K_M.gguf) | Q5_K_M | 23.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q6_K.gguf) | Q6_K | 27.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-32B-Thinking-abliterated-v1-GGUF/resolve/main/Qwen3-VL-32B-Thinking-abliterated-v1.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +