commit 868326e78a3dbb66ab01a1d803059ceff9270dc6 Author: ModelHub XC Date: Sun Jun 14 20:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-math-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5165e5d --- /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-math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-math.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-math.IQ4_XS.gguf b/Qwen3-4B-math.IQ4_XS.gguf new file mode 100644 index 0000000..13e06d7 --- /dev/null +++ b/Qwen3-4B-math.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df0e5bd5675b533feac497d7c3d4670da5dae95e6b6fd9490d26203e102bcfa +size 2286317888 diff --git a/Qwen3-4B-math.Q2_K.gguf b/Qwen3-4B-math.Q2_K.gguf new file mode 100644 index 0000000..1e14322 --- /dev/null +++ b/Qwen3-4B-math.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd45928efebcc4214a129bfff5b67c577e4f310313054a208bcfcc88fdfc38c1 +size 1669501248 diff --git a/Qwen3-4B-math.Q3_K_L.gguf b/Qwen3-4B-math.Q3_K_L.gguf new file mode 100644 index 0000000..7ad8fd9 --- /dev/null +++ b/Qwen3-4B-math.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b1c6f5e90bd4f4809db949aa49a9e9737f2388460980ec1efdc59bff484192 +size 2239787328 diff --git a/Qwen3-4B-math.Q3_K_M.gguf b/Qwen3-4B-math.Q3_K_M.gguf new file mode 100644 index 0000000..14a1f1e --- /dev/null +++ b/Qwen3-4B-math.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7e19a3dcd2cac1498efe830a8723630a5991d93fce19f018f370e01f58ac3e +size 2075619648 diff --git a/Qwen3-4B-math.Q3_K_S.gguf b/Qwen3-4B-math.Q3_K_S.gguf new file mode 100644 index 0000000..87c673c --- /dev/null +++ b/Qwen3-4B-math.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb0077947347f04190c6c2c5840f05a9876682d0bf1b46a58223aed5130ed9d +size 1886998848 diff --git a/Qwen3-4B-math.Q4_K_M.gguf b/Qwen3-4B-math.Q4_K_M.gguf new file mode 100644 index 0000000..812dc86 --- /dev/null +++ b/Qwen3-4B-math.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5ec9a179d04537cc0053c00c729607d1e88cccf2ca386f5fdc0fcba87e80ff +size 2497282368 diff --git a/Qwen3-4B-math.Q4_K_S.gguf b/Qwen3-4B-math.Q4_K_S.gguf new file mode 100644 index 0000000..80ee18a --- /dev/null +++ b/Qwen3-4B-math.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395f31b6cfe36490d3eb18f395b9cb809c932cc25982f4ca2db45349e9619f4f +size 2383311168 diff --git a/Qwen3-4B-math.Q5_K_M.gguf b/Qwen3-4B-math.Q5_K_M.gguf new file mode 100644 index 0000000..70c7a74 --- /dev/null +++ b/Qwen3-4B-math.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c4fde3c6be708ae2e47cb8f752ed13a3ae3b17a4280751ef8c4a5b9f184090 +size 2889515328 diff --git a/Qwen3-4B-math.Q5_K_S.gguf b/Qwen3-4B-math.Q5_K_S.gguf new file mode 100644 index 0000000..c319283 --- /dev/null +++ b/Qwen3-4B-math.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f750dfa7369c3f071e5c40480e883710f1d31e2639c37e4923443af357ff64f6 +size 2823713088 diff --git a/Qwen3-4B-math.Q6_K.gguf b/Qwen3-4B-math.Q6_K.gguf new file mode 100644 index 0000000..3bae0b9 --- /dev/null +++ b/Qwen3-4B-math.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb7338bd3c45a010a56292e9f99c0ebde1f1d8346fd211a3ed3a4d6ebb78321 +size 3306262848 diff --git a/Qwen3-4B-math.Q8_0.gguf b/Qwen3-4B-math.Q8_0.gguf new file mode 100644 index 0000000..541f55c --- /dev/null +++ b/Qwen3-4B-math.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd5ca818745fa5c092b6ed00339df286351657b3e3e4911e7978fd1461be890 +size 4280406848 diff --git a/Qwen3-4B-math.f16.gguf b/Qwen3-4B-math.f16.gguf new file mode 100644 index 0000000..5705d84 --- /dev/null +++ b/Qwen3-4B-math.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f955bec06ed63c8376ce9f4625a8c04a1ff3aafca99a275bb9f565b698f802 +size 8051286848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..457a925 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: wesjos/Qwen3-4B-math +datasets: +- unsloth/OpenMathReasoning-mini +- mlabonne/FineTome-100k +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +- math +--- +## About + + + + + + + + + +static quants of https://huggingface.co/wesjos/Qwen3-4B-math + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-math-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-math-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-math-GGUF/resolve/main/Qwen3-4B-math.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-math-GGUF/resolve/main/Qwen3-4B-math.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. + +