commit 7158ada914ef803665a8d358c2ca3b657ad475b2 Author: ModelHub XC Date: Wed Apr 22 19:48:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-MATH-R1-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3a5a610 --- /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-MATH-R1-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-MATH-R1-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-MATH-R1-4B.IQ4_XS.gguf b/Qwen3-MATH-R1-4B.IQ4_XS.gguf new file mode 100644 index 0000000..3d61c24 --- /dev/null +++ b/Qwen3-MATH-R1-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa201fad7a76bb150c6a110938c27438e9f66f7df9f1a36f35d53a94ae5286e +size 2286316896 diff --git a/Qwen3-MATH-R1-4B.Q2_K.gguf b/Qwen3-MATH-R1-4B.Q2_K.gguf new file mode 100644 index 0000000..6ed43c6 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3f884ab8eadd8dbb3404d5eedb67e5c14289342c216859ace853bf0fe6fffc +size 1669500256 diff --git a/Qwen3-MATH-R1-4B.Q3_K_L.gguf b/Qwen3-MATH-R1-4B.Q3_K_L.gguf new file mode 100644 index 0000000..b7b7904 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa36b5cb5d8b0e7021f868b67cd8c85af36f8fa602bf4effa4c198964d1beca +size 2239786336 diff --git a/Qwen3-MATH-R1-4B.Q3_K_M.gguf b/Qwen3-MATH-R1-4B.Q3_K_M.gguf new file mode 100644 index 0000000..ef561a1 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c92cba35c37c8558af10a4bbbebd7a3e0a15510ad9d90bd46b32195f850a9e +size 2075618656 diff --git a/Qwen3-MATH-R1-4B.Q3_K_S.gguf b/Qwen3-MATH-R1-4B.Q3_K_S.gguf new file mode 100644 index 0000000..33de220 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c32a0ccae282ede5b8ef26ecebfc703531676c81ba60ae5f55a3c931ac89249 +size 1886997856 diff --git a/Qwen3-MATH-R1-4B.Q4_K_M.gguf b/Qwen3-MATH-R1-4B.Q4_K_M.gguf new file mode 100644 index 0000000..caf89b5 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576b5f272e9f611174abbfbcfa5d03d4723dce663b4931f0fa46e35960370909 +size 2497281376 diff --git a/Qwen3-MATH-R1-4B.Q4_K_S.gguf b/Qwen3-MATH-R1-4B.Q4_K_S.gguf new file mode 100644 index 0000000..9423890 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17779d5e6ce5f54312255e493f3bd651a50ca36c5b9b393eefbbf7826c7867cd +size 2383310176 diff --git a/Qwen3-MATH-R1-4B.Q5_K_M.gguf b/Qwen3-MATH-R1-4B.Q5_K_M.gguf new file mode 100644 index 0000000..cd238df --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12dcfdaeb9f7f9bff9e118f3519ab91942c7259ede8f14f14ed9a6838cf878f7 +size 2889514336 diff --git a/Qwen3-MATH-R1-4B.Q5_K_S.gguf b/Qwen3-MATH-R1-4B.Q5_K_S.gguf new file mode 100644 index 0000000..fe1841c --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37521ee9c156663113c7d938911a8bdf92079d4d10ba82e19117f0af90b197ff +size 2823712096 diff --git a/Qwen3-MATH-R1-4B.Q6_K.gguf b/Qwen3-MATH-R1-4B.Q6_K.gguf new file mode 100644 index 0000000..6173cd2 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466e5ead4a631a058c1f07aabc3f4a7103f6c3db5c8e1ce5ed11e8d495832cbc +size 3306261856 diff --git a/Qwen3-MATH-R1-4B.Q8_0.gguf b/Qwen3-MATH-R1-4B.Q8_0.gguf new file mode 100644 index 0000000..90c55e7 --- /dev/null +++ b/Qwen3-MATH-R1-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92e1d59e97a5d8c3b3e2d4ddb1ffeedcf7fa36f1492635ddc75f6993788bb37 +size 4280405856 diff --git a/Qwen3-MATH-R1-4B.f16.gguf b/Qwen3-MATH-R1-4B.f16.gguf new file mode 100644 index 0000000..674f72a --- /dev/null +++ b/Qwen3-MATH-R1-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78aa02c9f02624ec74388cf4ca2f63a0ef42b7f8630cef177dfaa835da40e6e +size 8051285856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ac74fc --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Cannae-AI/Qwen3-MATH-R1-4B +datasets: +- nvidia/OpenMathReasoning +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- reasoning +- qwen3 +- math +- thinking +- conversational +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Cannae-AI/Qwen3-MATH-R1-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-MATH-R1-4B-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/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-MATH-R1-4B-GGUF/resolve/main/Qwen3-MATH-R1-4B.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. + +