commit b9b2e8f0ccf5038a46db7ee0b633068831c5d7bc Author: ModelHub XC Date: Sat Oct 24 01:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..490cad3 --- /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-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Reasoning.IQ4_XS.gguf b/Qwen3-4B-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..fb3fb19 --- /dev/null +++ b/Qwen3-4B-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5956bbe1aad4e90a0a923afd8f63a24c1eebfedcef820e0595df9a7a8c989c96 +size 2286313184 diff --git a/Qwen3-4B-Reasoning.Q2_K.gguf b/Qwen3-4B-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..9e78756 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4efbaa9dfd5483649a9bd7babb590c712695718d4aceb19a5fabbf6882e83c +size 1669496544 diff --git a/Qwen3-4B-Reasoning.Q3_K_L.gguf b/Qwen3-4B-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..0abcf33 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e284f171827db5f634aa2045b391252a703166c48a003cee66074df06c1627 +size 2239782624 diff --git a/Qwen3-4B-Reasoning.Q3_K_M.gguf b/Qwen3-4B-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..2505e1b --- /dev/null +++ b/Qwen3-4B-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4b982df0d28df8e1299aac03b24b2551939c70a6e5c2baf63c965fb9a34a03 +size 2075614944 diff --git a/Qwen3-4B-Reasoning.Q3_K_S.gguf b/Qwen3-4B-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..2db51b7 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6613240ce9698dc924cbdcca7d56802713767cc62d1c4b0b1a73dd215458b6 +size 1886994144 diff --git a/Qwen3-4B-Reasoning.Q4_K_M.gguf b/Qwen3-4B-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..a2f3ec5 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2725923e94dea245c2534a233d1fce38d1d8901a110ce408b5603ef27b1a4b6 +size 2497277664 diff --git a/Qwen3-4B-Reasoning.Q4_K_S.gguf b/Qwen3-4B-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..f5768d6 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e43a22751c4efa6387e516e0c1067ef6726fe151c71e44b8829c0ca66ac8634 +size 2383306464 diff --git a/Qwen3-4B-Reasoning.Q5_K_M.gguf b/Qwen3-4B-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..0344b8e --- /dev/null +++ b/Qwen3-4B-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef64c24f4c3a9a69336e71f805b612dcf59582debd577c30d2ccf9145f1b746c +size 2889510624 diff --git a/Qwen3-4B-Reasoning.Q5_K_S.gguf b/Qwen3-4B-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..62c4737 --- /dev/null +++ b/Qwen3-4B-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bcaffe9ee5c5aed3b01f17f0f10cf5a81ec8ed04d19a25958396fad5d430b0 +size 2823708384 diff --git a/Qwen3-4B-Reasoning.Q6_K.gguf b/Qwen3-4B-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..6fcf0db --- /dev/null +++ b/Qwen3-4B-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf34ec973ed29d9561fa3a47ed3d9f480d467f39869177ee7eec1019f2d7ebc +size 3306258144 diff --git a/Qwen3-4B-Reasoning.Q8_0.gguf b/Qwen3-4B-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..309ad3c --- /dev/null +++ b/Qwen3-4B-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5dfaf7ea09a8fd61f503d2641f22e68ff7c9562c565bdfeec8fb38824f1c21f +size 4280402144 diff --git a/Qwen3-4B-Reasoning.f16.gguf b/Qwen3-4B-Reasoning.f16.gguf new file mode 100644 index 0000000..0a63e60 --- /dev/null +++ b/Qwen3-4B-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c2210644dda63e8222e8b4535e7a149a85498689a7d0cdcefd2220998ff5f5 +size 8051282144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f258368 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: ZhengjunHUO/Qwen3-4B-Reasoning +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ZhengjunHUO/Qwen3-4B-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Reasoning-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Reasoning-GGUF/resolve/main/Qwen3-4B-Reasoning.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. + +