commit 15752a06f9bbf0f8b5be32657aea0098679c2c9e Author: ModelHub XC Date: Wed Jul 22 14:25:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Exp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..71ca9d8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Qwen3-4B-Exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Exp.IQ4_XS.gguf b/Qwen3-4B-Exp.IQ4_XS.gguf new file mode 100644 index 0000000..b1cd788 --- /dev/null +++ b/Qwen3-4B-Exp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2461cd8224bd2794f907bc4a771933d8dcc57bcaf316f95cad94e3bd6e38120d +size 2492945312 diff --git a/Qwen3-4B-Exp.Q2_K.gguf b/Qwen3-4B-Exp.Q2_K.gguf new file mode 100644 index 0000000..9ff56af --- /dev/null +++ b/Qwen3-4B-Exp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db163cffa6219cae138a8a14d1fbbad2758ddb65455b661ec8f5ec616f5257f0 +size 1797121952 diff --git a/Qwen3-4B-Exp.Q3_K_L.gguf b/Qwen3-4B-Exp.Q3_K_L.gguf new file mode 100644 index 0000000..6f11388 --- /dev/null +++ b/Qwen3-4B-Exp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3314ca6390ffcc2c01225671dcb198399f3b391fe9b5d2b8c0cce4fcbe66361d +size 2406911392 diff --git a/Qwen3-4B-Exp.Q3_K_M.gguf b/Qwen3-4B-Exp.Q3_K_M.gguf new file mode 100644 index 0000000..3f4456a --- /dev/null +++ b/Qwen3-4B-Exp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c12312b415298faec53048b020cf040b136fe2bbaaf2b774f916774224f6530 +size 2242743712 diff --git a/Qwen3-4B-Exp.Q3_K_S.gguf b/Qwen3-4B-Exp.Q3_K_S.gguf new file mode 100644 index 0000000..f6b6d40 --- /dev/null +++ b/Qwen3-4B-Exp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4f2c91055d823d03c58b807ca1b6fec4dac1d39d67754022e7d9a5695f54f2 +size 2054122912 diff --git a/Qwen3-4B-Exp.Q4_K_M.gguf b/Qwen3-4B-Exp.Q4_K_M.gguf new file mode 100644 index 0000000..7538647 --- /dev/null +++ b/Qwen3-4B-Exp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c4fa6ac6bb216a5dbb7a02953e0017011e5b25849154b6e9c60f6c6b02c698 +size 2716064672 diff --git a/Qwen3-4B-Exp.Q4_K_S.gguf b/Qwen3-4B-Exp.Q4_K_S.gguf new file mode 100644 index 0000000..7e32af9 --- /dev/null +++ b/Qwen3-4B-Exp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ac43ddb6a97fcf4f99c0b775c3fe946457458e75346b85aee0ca65774562cc +size 2602093472 diff --git a/Qwen3-4B-Exp.Q5_K_M.gguf b/Qwen3-4B-Exp.Q5_K_M.gguf new file mode 100644 index 0000000..05357b9 --- /dev/null +++ b/Qwen3-4B-Exp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6ecba8dfdd4a35e9d1005fb2adf8a43d0ad57d2b98aa0250030d599ba09b93 +size 3156917152 diff --git a/Qwen3-4B-Exp.Q5_K_S.gguf b/Qwen3-4B-Exp.Q5_K_S.gguf new file mode 100644 index 0000000..f27076c --- /dev/null +++ b/Qwen3-4B-Exp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bfb4c748f581ae2515adb7697f9c9f3afa1705de51e2abcb7a26404055d1be +size 3091114912 diff --git a/Qwen3-4B-Exp.Q6_K.gguf b/Qwen3-4B-Exp.Q6_K.gguf new file mode 100644 index 0000000..ba6ed83 --- /dev/null +++ b/Qwen3-4B-Exp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55eaab669ac11e78c02b2dabb46ad342d7a96d8d94c480cd7bf5e1688ab87254 +size 3625322912 diff --git a/Qwen3-4B-Exp.Q8_0.gguf b/Qwen3-4B-Exp.Q8_0.gguf new file mode 100644 index 0000000..2543dba --- /dev/null +++ b/Qwen3-4B-Exp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef55a60c9c657ab2bf1f9eabf0a85cf14d2dfabfd67a50bc63b6728b0d6ae6a +size 4693667232 diff --git a/Qwen3-4B-Exp.f16.gguf b/Qwen3-4B-Exp.f16.gguf new file mode 100644 index 0000000..c51f70b --- /dev/null +++ b/Qwen3-4B-Exp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264b2ca2a42417b43ddf9bb102715f6a09d272db08f41fb46d1660655e2be8b7 +size 8829193632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f905755 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: bunnycore/Qwen3-4B-Exp +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Roman0/Qwen3-4B-Instruct-2507-heretic +- Jackrong/GPT-5-Distill-Qwen3-4B-Instruct +- thinkwee/NOVER1-Qwen3-4B +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Exp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Exp-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Exp-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/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp-GGUF/resolve/main/Qwen3-4B-Exp.f16.gguf) | f16 | 8.9 | 16 bpw, overkill | + +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. + +