commit f5ddadcaf68977ba6b8f11eef6ccc51de522d521 Author: ModelHub XC Date: Tue Jun 2 16:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0410c3b --- /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 +Draconis-Qwen3_Math-4B-Preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Draconis-Qwen3_Math-4B-Preview.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Draconis-Qwen3_Math-4B-Preview.IQ4_XS.gguf b/Draconis-Qwen3_Math-4B-Preview.IQ4_XS.gguf new file mode 100644 index 0000000..3fc4316 --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de36d000969183d5f1bbb72217b4616779510bceb32ed5f34bbfa79ffb3c979f +size 2286317728 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q2_K.gguf b/Draconis-Qwen3_Math-4B-Preview.Q2_K.gguf new file mode 100644 index 0000000..40d268e --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c7c079b73837ef3f75e4767101c3e5954ed2273bcad7f8fa6b7fdc2341f38c +size 1669501088 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q3_K_L.gguf b/Draconis-Qwen3_Math-4B-Preview.Q3_K_L.gguf new file mode 100644 index 0000000..4f07547 --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2659f433c035fde592cd7c7f39428d4efc49705dc21b2aa4a2103dde84050b +size 2239787168 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q3_K_M.gguf b/Draconis-Qwen3_Math-4B-Preview.Q3_K_M.gguf new file mode 100644 index 0000000..2c91a6e --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ace324c62aac95ccf83b651fcf3cf17b6e275e3fcae9f25b5874f49fc77920 +size 2075619488 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q3_K_S.gguf b/Draconis-Qwen3_Math-4B-Preview.Q3_K_S.gguf new file mode 100644 index 0000000..469f702 --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e842271d7a7f16ece5fa0cf1d6b0d053ac77ea682b7eeba0f2a13a97e141d0 +size 1886998688 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q4_K_M.gguf b/Draconis-Qwen3_Math-4B-Preview.Q4_K_M.gguf new file mode 100644 index 0000000..39bf71f --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d2cd19713aa13d623309eea376954ad65a61c63f31a5eae40ac86c8c86dfb8 +size 2497282208 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q4_K_S.gguf b/Draconis-Qwen3_Math-4B-Preview.Q4_K_S.gguf new file mode 100644 index 0000000..a5dbccb --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a933a0cbf8b9569d399ad6a8411333a27e46a1ee7d4346f0ece040fdb1ef2d3 +size 2383311008 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q5_K_M.gguf b/Draconis-Qwen3_Math-4B-Preview.Q5_K_M.gguf new file mode 100644 index 0000000..36d5fbc --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed6f7d446f8e5d8980ce25e645fd42648f8f23de6c944eca00d38d301a3940c +size 2889515168 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q5_K_S.gguf b/Draconis-Qwen3_Math-4B-Preview.Q5_K_S.gguf new file mode 100644 index 0000000..91b905e --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5bb2dd189a7cb6127a429a0a658b19f205634f515f086bb107b8bdd739f9a53 +size 2823712928 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q6_K.gguf b/Draconis-Qwen3_Math-4B-Preview.Q6_K.gguf new file mode 100644 index 0000000..a20a0e7 --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3407fc1e134cf0674562aaec5b5c16c9a147665e92ac75b08df1c37cd8d62e +size 3306262688 diff --git a/Draconis-Qwen3_Math-4B-Preview.Q8_0.gguf b/Draconis-Qwen3_Math-4B-Preview.Q8_0.gguf new file mode 100644 index 0000000..5cdf046 --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77141feff6f4e160812ed2d072ecc4edb113eddb5dd25da61d9ca0bffe83926c +size 4280406688 diff --git a/Draconis-Qwen3_Math-4B-Preview.f16.gguf b/Draconis-Qwen3_Math-4B-Preview.f16.gguf new file mode 100644 index 0000000..d01112c --- /dev/null +++ b/Draconis-Qwen3_Math-4B-Preview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f306e97614859aeded44f5f3039370c1db330a31807a761228a8fc7206e6097 +size 8051286688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9ac5f2 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: prithivMLmods/Draconis-Qwen3_Math-4B-Preview +datasets: +- unsloth/OpenMathReasoning-mini +- mlabonne/FineTome-100k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- math +- code +- text-generation-inference +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Draconis-Qwen3_Math-4B-Preview + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Draconis-Qwen3_Math-4B-Preview-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/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Draconis-Qwen3_Math-4B-Preview-GGUF/resolve/main/Draconis-Qwen3_Math-4B-Preview.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. + +