commit a64a67f6ee9c23b3b4c62f23aa185b72161fb428 Author: ModelHub XC Date: Tue Jun 23 23:18:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8f455fe --- /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-Medical-Reasoning-0809.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Medical-Reasoning-0809.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Medical-Reasoning-0809.IQ4_XS.gguf b/Qwen3-4B-Medical-Reasoning-0809.IQ4_XS.gguf new file mode 100644 index 0000000..4f04fd5 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431926a716c646bff24300dd84817a020c22b69481b51ce62a7915a6921ceab0 +size 2286317440 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q2_K.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q2_K.gguf new file mode 100644 index 0000000..ac4fb01 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0eee502070d051d3beff56b8c3a053fe76efbc0014b07ddab81e7c5d03e504 +size 1669500800 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q3_K_L.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_L.gguf new file mode 100644 index 0000000..0828687 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1207ec9dd7910252821c830e772ebdcc9df8378e9db9c014084222343776816 +size 2239786880 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q3_K_M.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_M.gguf new file mode 100644 index 0000000..c4c5b35 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f27b404584ec940b434ed599188b876cf4a156f968ecd28bb1e4181405ef8b +size 2075619200 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q3_K_S.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_S.gguf new file mode 100644 index 0000000..8694a44 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497a4bcc53a3b39c11a6a9d67c104cf97c0ce03c85c7caaa01a74850ceffcc3d +size 1886998400 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q4_K_M.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q4_K_M.gguf new file mode 100644 index 0000000..8a9865b --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79659b85a63d1779551ba1dcf60e9350a547c5e9678fa7eeb6e195ce633ae14 +size 2497281920 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q4_K_S.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q4_K_S.gguf new file mode 100644 index 0000000..b46b04a --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ff661e531d00acbbf781c0e1084676199f98ce70a02a2b5d3f007ab90165ee +size 2383310720 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q5_K_M.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q5_K_M.gguf new file mode 100644 index 0000000..17bd726 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc6493de12dcbf3c88cd56c086aead280b911dba3f01f9c2880edffe2a77b0a +size 2889514880 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q5_K_S.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q5_K_S.gguf new file mode 100644 index 0000000..3aa42d9 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416cd1cf1bc363db62a751b59f50f135281c2ac2ae3c8ddb0781e97e25fcfa0c +size 2823712640 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q6_K.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q6_K.gguf new file mode 100644 index 0000000..0077cc8 --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5522d1b56238e6d504cfc5d23a57de7d9b2feeddcdc234b74526694a181df6bd +size 3306262400 diff --git a/Qwen3-4B-Medical-Reasoning-0809.Q8_0.gguf b/Qwen3-4B-Medical-Reasoning-0809.Q8_0.gguf new file mode 100644 index 0000000..763d5ff --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe49a4f6120a78a24f285b39c22aaaf1b176fb8c134e87e5f866a5723446ee97 +size 4280406400 diff --git a/Qwen3-4B-Medical-Reasoning-0809.f16.gguf b/Qwen3-4B-Medical-Reasoning-0809.f16.gguf new file mode 100644 index 0000000..050b5ea --- /dev/null +++ b/Qwen3-4B-Medical-Reasoning-0809.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab81b4870e38aeb7d961ee9460b4df1f98f683285cf0b7d3ae89e5245244ecd +size 8051286400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1064fb1 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ntkhoi/Qwen3-4B-Medical-Reasoning-0809 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ntkhoi/Qwen3-4B-Medical-Reasoning-0809 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Medical-Reasoning-0809-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/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Medical-Reasoning-0809-GGUF/resolve/main/Qwen3-4B-Medical-Reasoning-0809.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. + +