commit ca79be644e0acb338a30ed5123296fcbd0c7f986 Author: ModelHub XC Date: Wed Jun 3 04:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-dot-exp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e9d7e2 --- /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-dot-exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-dot-exp.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-dot-exp.IQ4_XS.gguf b/Qwen3-4B-dot-exp.IQ4_XS.gguf new file mode 100644 index 0000000..750c9a4 --- /dev/null +++ b/Qwen3-4B-dot-exp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa0fce12b21318825603c6d7a2bc9f8dff6fcbdc2dc66482cadd61d7063c0f0c +size 2286317248 diff --git a/Qwen3-4B-dot-exp.Q2_K.gguf b/Qwen3-4B-dot-exp.Q2_K.gguf new file mode 100644 index 0000000..86bd592 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52504177cd4b35e984b9d029e666a4a9a4278b32296542485a0dd8a127f2bcc2 +size 1669500608 diff --git a/Qwen3-4B-dot-exp.Q3_K_L.gguf b/Qwen3-4B-dot-exp.Q3_K_L.gguf new file mode 100644 index 0000000..b7c0906 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a627c37a319b8893e9f6678740e37347ec3aca8e089fee42179e8df845e4590 +size 2239786688 diff --git a/Qwen3-4B-dot-exp.Q3_K_M.gguf b/Qwen3-4B-dot-exp.Q3_K_M.gguf new file mode 100644 index 0000000..42a24e3 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af86b08304dea86eed4ea996c340d7942d38bc26d954beac63d6b1f46c5595f4 +size 2075619008 diff --git a/Qwen3-4B-dot-exp.Q3_K_S.gguf b/Qwen3-4B-dot-exp.Q3_K_S.gguf new file mode 100644 index 0000000..bc15cc4 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb5a900984445ee8fd5ade63c386473ff2d8b97c32c8f47c87be4585e9a6e12 +size 1886998208 diff --git a/Qwen3-4B-dot-exp.Q4_K_M.gguf b/Qwen3-4B-dot-exp.Q4_K_M.gguf new file mode 100644 index 0000000..9e684ad --- /dev/null +++ b/Qwen3-4B-dot-exp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749638848258177e251ceab73bbef93035bc1f73b95e26ffb05db1ea1e6f9614 +size 2497281728 diff --git a/Qwen3-4B-dot-exp.Q4_K_S.gguf b/Qwen3-4B-dot-exp.Q4_K_S.gguf new file mode 100644 index 0000000..c53d61d --- /dev/null +++ b/Qwen3-4B-dot-exp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4e15f61d55cf1e511d06bd0fa1597066292d30a86e341dd8541be596439ce72 +size 2383310528 diff --git a/Qwen3-4B-dot-exp.Q5_K_M.gguf b/Qwen3-4B-dot-exp.Q5_K_M.gguf new file mode 100644 index 0000000..4c53d16 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6801bf559f4eafec15430f02e29fef214cd65340b3cfdffb92150828f5b295f9 +size 2889514688 diff --git a/Qwen3-4B-dot-exp.Q5_K_S.gguf b/Qwen3-4B-dot-exp.Q5_K_S.gguf new file mode 100644 index 0000000..cbd3445 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a344598484f0fb9e37674553e867bf3da7675d80a0f8359a6979228e6fb54ab +size 2823712448 diff --git a/Qwen3-4B-dot-exp.Q6_K.gguf b/Qwen3-4B-dot-exp.Q6_K.gguf new file mode 100644 index 0000000..53da8fc --- /dev/null +++ b/Qwen3-4B-dot-exp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5486e75710f86a9d01c17df44e9e60b2a4b8fd5ce300bbff74d9d944371aa068 +size 3306262208 diff --git a/Qwen3-4B-dot-exp.Q8_0.gguf b/Qwen3-4B-dot-exp.Q8_0.gguf new file mode 100644 index 0000000..44a5443 --- /dev/null +++ b/Qwen3-4B-dot-exp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4fa1b5bd8c69cad33ec96d1cd53a14733f8c0e5767f5b54a1588e2b06b89ff +size 4280406208 diff --git a/Qwen3-4B-dot-exp.f16.gguf b/Qwen3-4B-dot-exp.f16.gguf new file mode 100644 index 0000000..547816d --- /dev/null +++ b/Qwen3-4B-dot-exp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b16a2204a021fbf9251c9777331cbe9d578e14ffe63a578f2d3ebc64b28f28 +size 8051286208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..350d530 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bunnycore/Qwen3-4B-dot-exp +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-dot-exp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-dot-exp-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-dot-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-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-dot-exp-GGUF/resolve/main/Qwen3-4B-dot-exp.f16.gguf) | f16 | 8.2 | 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. + +