commit 446d7e7bcd7e69bde8fbd0881a94513444093e66 Author: ModelHub XC Date: Tue Oct 13 06:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ruozhiReasoner-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eac4e68 --- /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 +ruozhiReasoner-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ruozhiReasoner-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5a5f34 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: XzWang/ruozhiReasoner-Qwen3-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/XzWang/ruozhiReasoner-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ruozhiReasoner-Qwen3-4B-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/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ruozhiReasoner-Qwen3-4B-GGUF/resolve/main/ruozhiReasoner-Qwen3-4B.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. + + diff --git a/ruozhiReasoner-Qwen3-4B.IQ4_XS.gguf b/ruozhiReasoner-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..636f293 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352d1550f4fe14bf25ac21021ee47fa4d4e49b21ccab202590dd3e3e3d3f6d89 +size 2286316256 diff --git a/ruozhiReasoner-Qwen3-4B.Q2_K.gguf b/ruozhiReasoner-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..23cec3c --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc94ee7f054a4f79fa94fc1fa2efa05fd2fe08cff21881b77ca61086c6e0231 +size 1669499616 diff --git a/ruozhiReasoner-Qwen3-4B.Q3_K_L.gguf b/ruozhiReasoner-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..ba94909 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed414df0787bf5ea30308080d8ef98278779028a8d08eadaef6710398de7b99 +size 2239785696 diff --git a/ruozhiReasoner-Qwen3-4B.Q3_K_M.gguf b/ruozhiReasoner-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..c5e2722 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7437e0954bb3cd992f92bb51e82cc1c418fe4d79d20c9b631e184dafaa590b67 +size 2075618016 diff --git a/ruozhiReasoner-Qwen3-4B.Q3_K_S.gguf b/ruozhiReasoner-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..a1b191c --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e0bfccaf044d26c0248092f09a7a2bd585ff2570eacddf37a78fc2386d39bce +size 1886997216 diff --git a/ruozhiReasoner-Qwen3-4B.Q4_K_M.gguf b/ruozhiReasoner-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..98e7158 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a19eef353681ffadfdbf3d72de62f5e0143e09cbe86b259f307f08d4dc08ca8 +size 2497280736 diff --git a/ruozhiReasoner-Qwen3-4B.Q4_K_S.gguf b/ruozhiReasoner-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..165f4d4 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f31f07dcbf7002ac94fbfb67dc82aff3ed67c6cb35ed92a98e1bed145a68044 +size 2383309536 diff --git a/ruozhiReasoner-Qwen3-4B.Q5_K_M.gguf b/ruozhiReasoner-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..f635510 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89492b558b42793ea9bff39566176661eca82e8547686d26cc28ceabc5dcde04 +size 2889513696 diff --git a/ruozhiReasoner-Qwen3-4B.Q5_K_S.gguf b/ruozhiReasoner-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..51931e6 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e861789e3babf6eb9865a75641d36a9309ec6e23d1589e4b5801e1d2f04969 +size 2823711456 diff --git a/ruozhiReasoner-Qwen3-4B.Q6_K.gguf b/ruozhiReasoner-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..2ae7348 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a52cc025f2d479019012ea033665183e5367de3bc6c0c9f6a69868ec1556082 +size 3306261216 diff --git a/ruozhiReasoner-Qwen3-4B.Q8_0.gguf b/ruozhiReasoner-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..066e9f8 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6ec41ca9d365b6c31e457594001e86ea914bf768cdfa647d302a314718da2c +size 4280405216 diff --git a/ruozhiReasoner-Qwen3-4B.f16.gguf b/ruozhiReasoner-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..05cc4c5 --- /dev/null +++ b/ruozhiReasoner-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109ed66a6202a27f44d32c1819ac5d0a753755da6d5577e02fe193d3c1eb37d3 +size 8051285216