commit f76c0669c169044daf84c589d77f722501e0c27d Author: ModelHub XC Date: Mon Jul 20 04:21:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4d49f6 --- /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-Distilled-30B-A3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Distilled-30B-A3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Distilled-30B-A3B.IQ4_XS.gguf b/Qwen3-0.6B-Distilled-30B-A3B.IQ4_XS.gguf new file mode 100644 index 0000000..54b102d --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d48bef4df61954aad6b2f97de114ec287024d07857b8ad4ee3fff828c81387 +size 451935424 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q2_K.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q2_K.gguf new file mode 100644 index 0000000..57ae925 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b57f0dea15ef17c6b8176b700f09e1f07c7589d133ed9878db099285e602cb +size 347292864 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_L.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_L.gguf new file mode 100644 index 0000000..a7548a4 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36b289d307c7ee34279e130075475a7b8ed1a4a0b79006f541ac349f0632bf3 +size 435347648 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_M.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_M.gguf new file mode 100644 index 0000000..3a6e065 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220236234779ace6690997c1c88fe30a4cafd02c8cbe0443c5a3be31111951d5 +size 413982912 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_S.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_S.gguf new file mode 100644 index 0000000..4da94fe --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3839034e5d15783ce0d066346d302c5a4bbc5546ff527fc65777c12ad1de5b1b +size 389931200 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_M.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_M.gguf new file mode 100644 index 0000000..55fcb54 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea54eba8275842b1d4b733230bd0197ae086d9bc961d6cd8e1bd27f80f097657 +size 484224192 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_S.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_S.gguf new file mode 100644 index 0000000..bc0e18f --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccf692256f13ae0d30134f1b7701013c16e7845912592ac6b61652edf025b80 +size 470789312 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_M.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_M.gguf new file mode 100644 index 0000000..bd47bd5 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc8d6b3c9ee5ad93a4ed1c48e66c2d22c3a8b5528314fcf94c3d7e88bc21573a +size 551382208 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_S.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_S.gguf new file mode 100644 index 0000000..c2b14c8 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e82f4ea74334a9a70aa6da867c427a95ad2896649f6a8e4f7ce8ca0f3b748ba +size 543583424 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q6_K.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q6_K.gguf new file mode 100644 index 0000000..5bbbf57 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c08507bb66398b62575bb89cd5c5df747b6f55a0cabcd62ff37400055074d4 +size 622737600 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.Q8_0.gguf b/Qwen3-0.6B-Distilled-30B-A3B.Q8_0.gguf new file mode 100644 index 0000000..be4f53a --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752742a3345820511534be986fce32bd13835d6391123e0ae66dc216846c63db +size 804757696 diff --git a/Qwen3-0.6B-Distilled-30B-A3B.f16.gguf b/Qwen3-0.6B-Distilled-30B-A3B.f16.gguf new file mode 100644 index 0000000..6562757 --- /dev/null +++ b/Qwen3-0.6B-Distilled-30B-A3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20d07df1a184fff9c5e5369a067494e0ce4ac5382ec4d4f7aa6a49ca071b119 +size 1509351616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..147bba2 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B +datasets: +- 0xZee/dataset-CoT-Advanced-Calculus-268 +- 0xZee/dataset-CoT-Modern-Physics-177 +- 0xZee/dataset-CoT-Theoretical-Mechanics-307 +- 0xZee/dataset-CoT-Linear-Algebra-667 +- 0xZee/dataset-CoT-Electromagnetism-580 +- 0xZee/dataset-CoT-Molecular-Biology-71 +- 0xZee/dataset-CoT-Physiology-114 +- 0xZee/dataset-CoT-Classical-Mechanics-343 +- 0xZee/dataset-CoT-Differential-Equations-636 +- 0xZee/dataset-CoT-Physics-2254 +- 0xZee/dataset-CoT-Engineering-574 +- 0xZee/dataset-CoT-mathematics +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- causal-lm +- text-generation +- distillation +- knowledge-distillation +- reasoning +- chain-of-thought +- mathematics +- physics +- engineering +- stem +- convergentintel +- edge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Distilled-30B-A3B-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-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.IQ4_XS.gguf) | IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Distilled-30B-A3B-GGUF/resolve/main/Qwen3-0.6B-Distilled-30B-A3B.f16.gguf) | f16 | 1.6 | 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. + +