commit 3e54687e561d604e29393b1d6d15b547a0e7a55b Author: ModelHub XC Date: Mon Apr 27 19:22:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedicalQwen3-Reasoning-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1308883 --- /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 +MedicalQwen3-Reasoning-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedicalQwen3-Reasoning-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedicalQwen3-Reasoning-4B.IQ4_XS.gguf b/MedicalQwen3-Reasoning-4B.IQ4_XS.gguf new file mode 100644 index 0000000..83762a4 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f6cea9aa62591aeb5f99299b82da01c2bc51562191698b95e62d60488c9a78 +size 2286317760 diff --git a/MedicalQwen3-Reasoning-4B.Q2_K.gguf b/MedicalQwen3-Reasoning-4B.Q2_K.gguf new file mode 100644 index 0000000..8550b37 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22182f10af4efdef45d6e56e662c7c1baabf187c3a1d94c5307327278fad958 +size 1669501120 diff --git a/MedicalQwen3-Reasoning-4B.Q3_K_L.gguf b/MedicalQwen3-Reasoning-4B.Q3_K_L.gguf new file mode 100644 index 0000000..df3a994 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0f9829e17f56222e11680547b5cc9736bac25893bb9e868f39bcf3ce6006d4 +size 2239787200 diff --git a/MedicalQwen3-Reasoning-4B.Q3_K_M.gguf b/MedicalQwen3-Reasoning-4B.Q3_K_M.gguf new file mode 100644 index 0000000..1a3635b --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b926bd06a74049c1bb7229e5515467c2b6e74ca196b9935c4843ac0d6c7445d +size 2075619520 diff --git a/MedicalQwen3-Reasoning-4B.Q3_K_S.gguf b/MedicalQwen3-Reasoning-4B.Q3_K_S.gguf new file mode 100644 index 0000000..6f0fe50 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12da4bad1cc5b51e4e05765bf8ec7a5e29a846da8c37ee82e6a66157ac43c7d +size 1886998720 diff --git a/MedicalQwen3-Reasoning-4B.Q4_K_M.gguf b/MedicalQwen3-Reasoning-4B.Q4_K_M.gguf new file mode 100644 index 0000000..3ab42a1 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea126c1e1e6ab93eaa549c2a44d93d8f768cb3efce96e4e1553716251f6ce248 +size 2497282240 diff --git a/MedicalQwen3-Reasoning-4B.Q4_K_S.gguf b/MedicalQwen3-Reasoning-4B.Q4_K_S.gguf new file mode 100644 index 0000000..2000bc2 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb42ae43c7e475cd178c7c57eec16a22785353aadb48578ceccfc6062a9caa6 +size 2383311040 diff --git a/MedicalQwen3-Reasoning-4B.Q5_K_M.gguf b/MedicalQwen3-Reasoning-4B.Q5_K_M.gguf new file mode 100644 index 0000000..cb9f79a --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4796dc8549c816fd14766d857a2b2a26ad2dab2b96f0cc170c1d0bd7d0350b10 +size 2889515200 diff --git a/MedicalQwen3-Reasoning-4B.Q5_K_S.gguf b/MedicalQwen3-Reasoning-4B.Q5_K_S.gguf new file mode 100644 index 0000000..b923e47 --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37343c64057402571cf0290f76ef95302d2cdb263984d223159a91f5566b4104 +size 2823712960 diff --git a/MedicalQwen3-Reasoning-4B.Q6_K.gguf b/MedicalQwen3-Reasoning-4B.Q6_K.gguf new file mode 100644 index 0000000..8669bfd --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fec5e6f325d3358359af97f343ba70f5d87a0aed04ac5af9728d51a23f10010 +size 3306262720 diff --git a/MedicalQwen3-Reasoning-4B.Q8_0.gguf b/MedicalQwen3-Reasoning-4B.Q8_0.gguf new file mode 100644 index 0000000..09e7b9a --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab990cffe03e97adc8db8d41025dc14bb243e8dc96b728335b96a3d399cb611b +size 4280406720 diff --git a/MedicalQwen3-Reasoning-4B.f16.gguf b/MedicalQwen3-Reasoning-4B.f16.gguf new file mode 100644 index 0000000..521c5fb --- /dev/null +++ b/MedicalQwen3-Reasoning-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befe8e662682fb0f98c89c8772c867b039a3dd8de2a40e76e65ce49a01d94a86 +size 8051286720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..221c93a --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Cannae-AI/MedicalQwen3-Reasoning-4B +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +- Mohammed-Altaf/medical-instruction-120k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- qwen3 +- medical +- reasoning +- clinical +- healthcare +- biology +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Cannae-AI/MedicalQwen3-Reasoning-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedicalQwen3-Reasoning-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-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/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedicalQwen3-Reasoning-4B-GGUF/resolve/main/MedicalQwen3-Reasoning-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. + +