commit 8987272ef0336c7dd203a00f6ad10f7ce95393d1 Author: ModelHub XC Date: Tue Apr 28 13:33:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45235f4 --- /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 +ReD-Qwen3-4B-Thinking-Search.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ReD-Qwen3-4B-Thinking-Search.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bb40f42 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: jiulaikankan/ReD-Qwen3-4B-Thinking-Search +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jiulaikankan/ReD-Qwen3-4B-Thinking-Search + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ReD-Qwen3-4B-Thinking-Search-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/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ReD-Qwen3-4B-Thinking-Search-GGUF/resolve/main/ReD-Qwen3-4B-Thinking-Search.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. + + diff --git a/ReD-Qwen3-4B-Thinking-Search.IQ4_XS.gguf b/ReD-Qwen3-4B-Thinking-Search.IQ4_XS.gguf new file mode 100644 index 0000000..723f328 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a658534e5639cbb2a12dc3518dfa2c8aa96b9aa67d03cb899d8de38a5abe67bd +size 2286316672 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q2_K.gguf b/ReD-Qwen3-4B-Thinking-Search.Q2_K.gguf new file mode 100644 index 0000000..44fc8e4 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bd7d0eedf5ec21667b99e7876a597821ce2cbe887650183efe74a3b524ec2f +size 1669500032 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q3_K_L.gguf b/ReD-Qwen3-4B-Thinking-Search.Q3_K_L.gguf new file mode 100644 index 0000000..b06a009 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98575418c174eaea6b06b6bea316fd8f301ee7d649c8dae9ebcb09183554c98d +size 2239786112 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q3_K_M.gguf b/ReD-Qwen3-4B-Thinking-Search.Q3_K_M.gguf new file mode 100644 index 0000000..5814db1 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e37f2ed5462155105a018f02b74fb246e667940a8cb8035948d9e1fb796441a +size 2075618432 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q3_K_S.gguf b/ReD-Qwen3-4B-Thinking-Search.Q3_K_S.gguf new file mode 100644 index 0000000..73d0b12 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ccf1e68318a3162c69107dd5f75bc5ff31774ce2742b402c3318b9310bf9413 +size 1886997632 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q4_K_M.gguf b/ReD-Qwen3-4B-Thinking-Search.Q4_K_M.gguf new file mode 100644 index 0000000..eb2f07a --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5883a472468be96cc80a162d76549b35b6199566127c9be913062a7285242315 +size 2497281152 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q4_K_S.gguf b/ReD-Qwen3-4B-Thinking-Search.Q4_K_S.gguf new file mode 100644 index 0000000..0ec706f --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80980a7e57d819ee791f7dcc20e54f94ca7c0d0c7916656fe166147a5691949 +size 2383309952 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q5_K_M.gguf b/ReD-Qwen3-4B-Thinking-Search.Q5_K_M.gguf new file mode 100644 index 0000000..fcf1de1 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449019a07428ac97b217466c95a0359fd1cbe85e55bd675b4a0c5e39e0e65960 +size 2889514112 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q5_K_S.gguf b/ReD-Qwen3-4B-Thinking-Search.Q5_K_S.gguf new file mode 100644 index 0000000..9a7fdd0 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881cf6591f056def0c59e5be1791bf43a0d612576dbda43fafbda7cdebe34989 +size 2823711872 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q6_K.gguf b/ReD-Qwen3-4B-Thinking-Search.Q6_K.gguf new file mode 100644 index 0000000..50f59b4 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf95bc0adbf4a270ac17d7e6b467cede7bcea77a1ed52cdb60577ddd4e1e962 +size 3306261632 diff --git a/ReD-Qwen3-4B-Thinking-Search.Q8_0.gguf b/ReD-Qwen3-4B-Thinking-Search.Q8_0.gguf new file mode 100644 index 0000000..f9b311a --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba33c0fb6cfe3d1ac0b41b1cd9b43708d1bb3d2b901a33891a6ce49f01855fe1 +size 4280405632 diff --git a/ReD-Qwen3-4B-Thinking-Search.f16.gguf b/ReD-Qwen3-4B-Thinking-Search.f16.gguf new file mode 100644 index 0000000..761d689 --- /dev/null +++ b/ReD-Qwen3-4B-Thinking-Search.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3945fa031d13e3ddfb8bc5dca2f6f7a5a1af2d1a4828ea579fc483cbe0eac028 +size 8051285632