commit 9f4cf05f82d256ed4daa0e000efd927ba66890b2 Author: ModelHub XC Date: Sat Jun 20 01:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5bbabc6 --- /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 +GCCL-Medical-LLM-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GCCL-Medical-LLM-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GCCL-Medical-LLM-Qwen3-4B.IQ4_XS.gguf b/GCCL-Medical-LLM-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..9f5a477 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d889775f029c505a9af79d88d5aebe2450e5c900161101c6ccd92bfe9e77ef +size 2286315168 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q2_K.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..7e849ba --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb91bcca0012162dfbf412945a4e0e706a99c1abd800a7db595cb399429f552e +size 1669498528 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q3_K_L.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..376325f --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dfe924b37905fbe16794d9eca139e19c34adf5030d270f9ff1aa2c7f6e9c944 +size 2239784608 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q3_K_M.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..60b74a5 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5db53f4c2ef765defa496c71ee63e2ce9893c5a2534795061369f6e1628a896 +size 2075616928 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q3_K_S.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..902405c --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee52c07a5dec5028140f3987d605dd050eb0fcab465c81d0566d4962e74ef5b9 +size 1886996128 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q4_K_M.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..cbd2eb5 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7d251b57c9a6472c7b52a6cdab12e1cd7a3a7c95cf4c5e4a030d278720b43f +size 2497279648 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q4_K_S.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..53f1142 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975382099f1cdd6a55d432deb958a6d6bcd8767006a6d6a051c542987cda8b34 +size 2383308448 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q5_K_M.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..f852549 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5938f2cbeb3a3708f71448c84e1f3ccc2dde8da2d63fe7382496921abfe6f043 +size 2889512608 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q5_K_S.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..d82c133 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e19e82baa79faff16de922a458f4628bf6d7b11c86f0788259e67634d61cea +size 2823710368 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q6_K.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..de39284 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9f184099095906251f19cb42d8839d42b87a398b50bae6581dcab6bd853d67 +size 3306260128 diff --git a/GCCL-Medical-LLM-Qwen3-4B.Q8_0.gguf b/GCCL-Medical-LLM-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..37449e4 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549acb79a499337399935c7136a50714153e3bf53f0323e021a7fc6c6730875e +size 4280404128 diff --git a/GCCL-Medical-LLM-Qwen3-4B.f16.gguf b/GCCL-Medical-LLM-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..884ae11 --- /dev/null +++ b/GCCL-Medical-LLM-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb8128c073d485f1aa1cb30e271cc38cc6651244ed954abfef780a143f45263 +size 8051284128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e1ee95 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: z8086486/GCCL-Medical-LLM-Qwen3-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/z8086486/GCCL-Medical-LLM-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GCCL-Medical-LLM-Qwen3-4B-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/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GCCL-Medical-LLM-Qwen3-4B-GGUF/resolve/main/GCCL-Medical-LLM-Qwen3-4B.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. + +