commit 454eae9e9bcced31f53f72fa20b9ee4a78d9896c Author: ModelHub XC Date: Mon Jul 20 05:25:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b47b0bf --- /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-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Thinking.IQ4_XS.gguf b/Qwen3-0.6B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..9c7eba5 --- /dev/null +++ b/Qwen3-0.6B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f164f1d1727b1ad624ba4a10178769e29974cddd7a94f7ba2766eb715ac0e262 +size 369278400 diff --git a/Qwen3-0.6B-Thinking.Q2_K.gguf b/Qwen3-0.6B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..5e13dfa --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2484dcd8fe19f111fb7d64694f289bd64f3ce1bc25a2346caefc21988eb0680a +size 296238528 diff --git a/Qwen3-0.6B-Thinking.Q3_K_L.gguf b/Qwen3-0.6B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..2e277cd --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c712646715c4d604d050c89da3df128f4cdafe6995d33603617b3fb5a2ca47e8 +size 368491968 diff --git a/Qwen3-0.6B-Thinking.Q3_K_M.gguf b/Qwen3-0.6B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..7da9ea8 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf52873e720d22c9f6cc1eb5c766ca2515ae6d7a35372bf7995180f0e3283da +size 347127232 diff --git a/Qwen3-0.6B-Thinking.Q3_K_S.gguf b/Qwen3-0.6B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..bd35b42 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d142322981b80116d3f9a5c5475cc7d42b9a8c9336bce64b095d2df4cf01bb +size 323075520 diff --git a/Qwen3-0.6B-Thinking.Q4_K_M.gguf b/Qwen3-0.6B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..3b0e223 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bce6453df4a45b690bf8635b5c74f28ab3c729f04c4ecbd703303173edd575 +size 396705216 diff --git a/Qwen3-0.6B-Thinking.Q4_K_S.gguf b/Qwen3-0.6B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..58ba819 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85b1bd9a87bb3e224cf3e88c4f7f22d93ab46549435dc34fb56ffa2f9825892 +size 383270336 diff --git a/Qwen3-0.6B-Thinking.Q5_K_M.gguf b/Qwen3-0.6B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..96482d3 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878ab9c180cb56dedde98c40d185ccf060cb1cffcbbb65ca02d065c1906abe9c +size 444415424 diff --git a/Qwen3-0.6B-Thinking.Q5_K_S.gguf b/Qwen3-0.6B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..9a1f70a --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77102cb4ef13acae269f9e85d0f50f6985ba3b926fb8a7de10e6241fd96e9ebd +size 436616640 diff --git a/Qwen3-0.6B-Thinking.Q6_K.gguf b/Qwen3-0.6B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..ed954c8 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6d8bf8deec0b22a3b4f4eb77c3af12f6e83c9a352b8221b9b2b8db0938b9a1 +size 495107520 diff --git a/Qwen3-0.6B-Thinking.Q8_0.gguf b/Qwen3-0.6B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..2cc5774 --- /dev/null +++ b/Qwen3-0.6B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91028d1c7562f5f72f96c222a799668488e790527d6cf8864f1aacca6eb4163b +size 639447488 diff --git a/Qwen3-0.6B-Thinking.f16.gguf b/Qwen3-0.6B-Thinking.f16.gguf new file mode 100644 index 0000000..c5168c5 --- /dev/null +++ b/Qwen3-0.6B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c623877727516f2d7c49a3bfd35d5fb4f7c9bc37f38d761d1c7ede924d5723e4 +size 1198182848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..010ef10 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Jackrong/Qwen3-0.6B-Thinking +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/Qwen3-0.6B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Thinking-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-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Thinking-GGUF/resolve/main/Qwen3-0.6B-Thinking.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. + +