commit 45201ec32216c2e896d1fce1a8ebf66e68acd2b3 Author: ModelHub XC Date: Thu Oct 15 08:00:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Mini-Think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ff7b92 --- /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 +Qwen3-4B-Mini-Think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Mini-Think.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Mini-Think.IQ4_XS.gguf b/Qwen3-4B-Mini-Think.IQ4_XS.gguf new file mode 100644 index 0000000..c002b3e --- /dev/null +++ b/Qwen3-4B-Mini-Think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366e11936f22e85ca208be303c6756cee32af0a0053d44cc9595958044d562f4 +size 2286313056 diff --git a/Qwen3-4B-Mini-Think.Q2_K.gguf b/Qwen3-4B-Mini-Think.Q2_K.gguf new file mode 100644 index 0000000..4828110 --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b30b32e457cc490f114dc8a4beb3d4d99b5d0a068aae24b5ca6a04337b8470 +size 1669496416 diff --git a/Qwen3-4B-Mini-Think.Q3_K_L.gguf b/Qwen3-4B-Mini-Think.Q3_K_L.gguf new file mode 100644 index 0000000..4dba279 --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d83e7cc09033a63bc96a8619d01ecddb67bd2b067d9418d278078813013cbb +size 2239782496 diff --git a/Qwen3-4B-Mini-Think.Q3_K_M.gguf b/Qwen3-4B-Mini-Think.Q3_K_M.gguf new file mode 100644 index 0000000..1d25dae --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea650c9ba7d5f63037d595252b9826d4574f46800855b73a2b1a9bc22d9d5ca +size 2075614816 diff --git a/Qwen3-4B-Mini-Think.Q3_K_S.gguf b/Qwen3-4B-Mini-Think.Q3_K_S.gguf new file mode 100644 index 0000000..e2a89af --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19196fb5e157af957e6f7d41149db3aa0571f0114f9631331c60d89e09da2eef +size 1886994016 diff --git a/Qwen3-4B-Mini-Think.Q4_K_M.gguf b/Qwen3-4B-Mini-Think.Q4_K_M.gguf new file mode 100644 index 0000000..2ef61af --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4431cd6a3dc306e5545c701480fce4bcbbf0833c9c46803d64d3a4eeb7448c +size 2497277536 diff --git a/Qwen3-4B-Mini-Think.Q4_K_S.gguf b/Qwen3-4B-Mini-Think.Q4_K_S.gguf new file mode 100644 index 0000000..c4af906 --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0603843685cce9629b045cc7792b74b91c0a05a8a56c1a20d68fcb1090acec0 +size 2383306336 diff --git a/Qwen3-4B-Mini-Think.Q5_K_M.gguf b/Qwen3-4B-Mini-Think.Q5_K_M.gguf new file mode 100644 index 0000000..91fd8b9 --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edeaa12a67e2ebc22f27ed760f62477f6b2eaecbf8b71382ac75daddaffc3f08 +size 2889510496 diff --git a/Qwen3-4B-Mini-Think.Q5_K_S.gguf b/Qwen3-4B-Mini-Think.Q5_K_S.gguf new file mode 100644 index 0000000..8a5f3d9 --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb1819536bbd504f3484e4bf35144bc87781c35091cdcdc4f3f610e16932b9d +size 2823708256 diff --git a/Qwen3-4B-Mini-Think.Q6_K.gguf b/Qwen3-4B-Mini-Think.Q6_K.gguf new file mode 100644 index 0000000..77d361e --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d53e3d155f539e791a6786cd7d5125c789b3d5cb029c34aac5672b8fb008d2 +size 3306258016 diff --git a/Qwen3-4B-Mini-Think.Q8_0.gguf b/Qwen3-4B-Mini-Think.Q8_0.gguf new file mode 100644 index 0000000..21fa65d --- /dev/null +++ b/Qwen3-4B-Mini-Think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86d0389740dd639eb44221200890c0f2291b6b3540e5aa34924c16aad03a7cf8 +size 4280402016 diff --git a/Qwen3-4B-Mini-Think.f16.gguf b/Qwen3-4B-Mini-Think.f16.gguf new file mode 100644 index 0000000..87e2da0 --- /dev/null +++ b/Qwen3-4B-Mini-Think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b3a3d56a43fabd397f8c20291dec70ad4ced7b27dfd2c35e8f4ea829de6404 +size 8051282016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86b8500 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: bunnycore/Qwen3-4B-Mini-Think +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- TeichAI/Qwen3-4B-Thinking-MiniMax-M2.1-Coder +- TeichAI/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Mini-Think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Mini-Think-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-i1-GGUF +## 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/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Mini-Think-GGUF/resolve/main/Qwen3-4B-Mini-Think.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. + +