commit d67eb1d7874dc50e5573d2062ae686d57ecf604b Author: ModelHub XC Date: Fri May 8 17:14:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Math-Expert-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cb36aff --- /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 +Qwen3-0.6B-Math-Expert.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Math-Expert.IQ4_XS.gguf b/Qwen3-0.6B-Math-Expert.IQ4_XS.gguf new file mode 100644 index 0000000..1eeca8f --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:424bec693c0293b1daee585cc2e6d14666dc294f80dc0b650944116cae3e0043 +size 369279360 diff --git a/Qwen3-0.6B-Math-Expert.Q2_K.gguf b/Qwen3-0.6B-Math-Expert.Q2_K.gguf new file mode 100644 index 0000000..5967348 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4953fa8d7ec84fa468800118e6c72419cedb697d92aa1d3e7c4db90d39d7c600 +size 296239488 diff --git a/Qwen3-0.6B-Math-Expert.Q3_K_L.gguf b/Qwen3-0.6B-Math-Expert.Q3_K_L.gguf new file mode 100644 index 0000000..18365c4 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfee16304abc357aae2c9e54203e8de5d06dbbd14f63ee79dfa4ad7d88a8d390 +size 368492928 diff --git a/Qwen3-0.6B-Math-Expert.Q3_K_M.gguf b/Qwen3-0.6B-Math-Expert.Q3_K_M.gguf new file mode 100644 index 0000000..a7cd01c --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc6b6c74bb9f538f4c5ac42382a93d0ce70ab20e6facc92d15ca53375f85601 +size 347128192 diff --git a/Qwen3-0.6B-Math-Expert.Q3_K_S.gguf b/Qwen3-0.6B-Math-Expert.Q3_K_S.gguf new file mode 100644 index 0000000..a750d3c --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a120570dba0aeb40f530e5e28cf658363d65b1d2fcadd238065f9a9bcdabf2a +size 323076480 diff --git a/Qwen3-0.6B-Math-Expert.Q4_K_M.gguf b/Qwen3-0.6B-Math-Expert.Q4_K_M.gguf new file mode 100644 index 0000000..efeb031 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f64c2e3bbd5c6fa570f49631cad5527ebd4acd7fcaf014963152027b2dae9a1 +size 396706176 diff --git a/Qwen3-0.6B-Math-Expert.Q4_K_S.gguf b/Qwen3-0.6B-Math-Expert.Q4_K_S.gguf new file mode 100644 index 0000000..7bceadc --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ae98072effa5e3b8f7d1c32aebf4c6358cc624a2a8169f64bbc6b74910f511 +size 383271296 diff --git a/Qwen3-0.6B-Math-Expert.Q5_K_M.gguf b/Qwen3-0.6B-Math-Expert.Q5_K_M.gguf new file mode 100644 index 0000000..f1db477 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d87cab1a3f345e061c55f00c84556a7b7527176a7bd6d3af0bbf1eaa73137f4 +size 444416384 diff --git a/Qwen3-0.6B-Math-Expert.Q5_K_S.gguf b/Qwen3-0.6B-Math-Expert.Q5_K_S.gguf new file mode 100644 index 0000000..5329850 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835a47368ffc878813ef505578d3b102c80f7628d405800f0f0cc0d6356a5717 +size 436617600 diff --git a/Qwen3-0.6B-Math-Expert.Q6_K.gguf b/Qwen3-0.6B-Math-Expert.Q6_K.gguf new file mode 100644 index 0000000..b6c4e9e --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96c6ed1efc8042a236a60e1f4a19873db13c65015ca5918f191adde2ab4ea03 +size 495108480 diff --git a/Qwen3-0.6B-Math-Expert.Q8_0.gguf b/Qwen3-0.6B-Math-Expert.Q8_0.gguf new file mode 100644 index 0000000..ea1a9cb --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100a145f738f6ef5e21321fab354215293fb8317cd01215028b62ab09c22ad92 +size 639448448 diff --git a/Qwen3-0.6B-Math-Expert.f16.gguf b/Qwen3-0.6B-Math-Expert.f16.gguf new file mode 100644 index 0000000..ff2a263 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bbe6896d75e7f9a3e70f162e7d37cc3bd55df98faeeea5be0ed15fb18e8fef5 +size 1198183808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a671b98 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: suayptalha/Qwen3-0.6B-Math-Expert +datasets: +- unsloth/OpenMathReasoning-mini +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- math +- reasoning +--- +## About + + + + + + +static quants of https://huggingface.co/suayptalha/Qwen3-0.6B-Math-Expert + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Math-Expert-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/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-GGUF/resolve/main/Qwen3-0.6B-Math-Expert.f16.gguf) | f16 | 1.3 | 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. + +