commit ac15538707b431d851fb28cb032dbbb4c27b305a Author: ModelHub XC Date: Sat Jul 18 02:30:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NINA-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a4d3c5 --- /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 +NINA-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NINA-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NINA-Qwen3-4B.IQ4_XS.gguf b/NINA-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..0c9c08b --- /dev/null +++ b/NINA-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b014daca074717e050558ee1b81ae14092ed3951b9fedfe62d4f6ddec89de25a +size 2286316576 diff --git a/NINA-Qwen3-4B.Q2_K.gguf b/NINA-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..2660eb7 --- /dev/null +++ b/NINA-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688bc2dfad858d97be6498387b935207a9d1af02a02a34bbc9563cc645540f77 +size 1669499936 diff --git a/NINA-Qwen3-4B.Q3_K_L.gguf b/NINA-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..9236d35 --- /dev/null +++ b/NINA-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0d9117c7b91e0092c82ef502ca8ede73fe6fbfab521098c01410741f693ed0 +size 2239786016 diff --git a/NINA-Qwen3-4B.Q3_K_M.gguf b/NINA-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..fa91808 --- /dev/null +++ b/NINA-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0e555a66b2e1f6f980b2758d40c036c83fddfdd56d0fff6e108b4b9c9ae208 +size 2075618336 diff --git a/NINA-Qwen3-4B.Q3_K_S.gguf b/NINA-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..948ad4c --- /dev/null +++ b/NINA-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97c1cae505e5761ade1ef9c7540747b69dfe6afee209bb02da0f163ea5b2d35 +size 1886997536 diff --git a/NINA-Qwen3-4B.Q4_K_M.gguf b/NINA-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..923cb3a --- /dev/null +++ b/NINA-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2301c5f77dbf2d2c7d8ab49d5b39834193cce264a06f3e74216a4ecadcc8a4ed +size 2497281056 diff --git a/NINA-Qwen3-4B.Q4_K_S.gguf b/NINA-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..08853a2 --- /dev/null +++ b/NINA-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff3d3e7b02cd80dea91729917f7e316dedda56fb776161273a2a72d0bdc33a0 +size 2383309856 diff --git a/NINA-Qwen3-4B.Q5_K_M.gguf b/NINA-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..9d08946 --- /dev/null +++ b/NINA-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b0718ec51e4ffe023c6c52e68ebdca7a75a40d6ee8349004539a838fffe2355 +size 2889514016 diff --git a/NINA-Qwen3-4B.Q5_K_S.gguf b/NINA-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..0ba7d0a --- /dev/null +++ b/NINA-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae961cf922327a4d78f7f91e5507152ef27a052a45dbfb4fee7426ab1ae2982 +size 2823711776 diff --git a/NINA-Qwen3-4B.Q6_K.gguf b/NINA-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..d27abf9 --- /dev/null +++ b/NINA-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9d13010f57e0070eeb3da83a32bf750e2eca93e5e15637932bf7a674dde6be +size 3306261536 diff --git a/NINA-Qwen3-4B.Q8_0.gguf b/NINA-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..3a8e3e5 --- /dev/null +++ b/NINA-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa292a8f2d602c675c9f3ea46de154b58fec5ca5de24da4efa03fac742d4eca +size 4280405536 diff --git a/NINA-Qwen3-4B.f16.gguf b/NINA-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..4b1fc05 --- /dev/null +++ b/NINA-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d06d9927382f257220ed75fb8ae325240136428c382daac419b15e716e3b6216 +size 8051285536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b538c3c --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Vincenzo2K04/NINA-Qwen3-4B +language: en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen3 +- healthcare +- nursing +- guardrails +- fine-tuned +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Vincenzo2K04/NINA-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NINA-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/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NINA-Qwen3-4B-GGUF/resolve/main/NINA-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. + +