commit 6bee45c631178f9a944acddd7033eea9ed5bfa74 Author: ModelHub XC Date: Tue Sep 1 01:16:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e165dab --- /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 +DAFT-Qwen3-4B-Instruct-2507.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DAFT-Qwen3-4B-Instruct-2507.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DAFT-Qwen3-4B-Instruct-2507.IQ4_XS.gguf b/DAFT-Qwen3-4B-Instruct-2507.IQ4_XS.gguf new file mode 100644 index 0000000..ace2ff2 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9ab2d93f5bc5bc44b1478c73148851c7d830469b435cccbd7580bf87e6b09f +size 2286314944 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q2_K.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q2_K.gguf new file mode 100644 index 0000000..dd79ea2 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15841431255ea7a17803105a0d0aeefdf55f5a783bc8ca24955bedc8018bbf8c +size 1669498304 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q3_K_L.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_L.gguf new file mode 100644 index 0000000..cbfc799 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc31e7f05373166d4bf11d36cc616c9407204a81468220824069cbddbaec4960 +size 2239784384 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q3_K_M.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_M.gguf new file mode 100644 index 0000000..30f5ad8 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfac0abc5c7901c643c33a3fdb4603e11f9872c446cdf92658b456fcc3514adc +size 2075616704 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q3_K_S.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_S.gguf new file mode 100644 index 0000000..7db5d67 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9db4a3b3ab7a15d56f4952be81737d72d60639d1ccf405776a944da834c73ae +size 1886995904 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q4_K_M.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q4_K_M.gguf new file mode 100644 index 0000000..85a9a93 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280ef0d8efeecb4a777d5752429596789bdcf8d1553290a126685f296b0ae080 +size 2497279424 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q4_K_S.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q4_K_S.gguf new file mode 100644 index 0000000..bfbb3d8 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd31562a7f2313f2445c0111ee29feef32d4e90ec18920a83a23203331864a16 +size 2383308224 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q5_K_M.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q5_K_M.gguf new file mode 100644 index 0000000..487ebd9 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b3c1eaecb749dfd307f5f8da1f8883ca8a9621b327947aa49e103ee87d6a23 +size 2889512384 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q5_K_S.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q5_K_S.gguf new file mode 100644 index 0000000..f9f3144 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4d529018eb558230209502a588be352d9daf36250a526a498d910dcc827510 +size 2823710144 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q6_K.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q6_K.gguf new file mode 100644 index 0000000..7c2c63d --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3503a9266a4c58e4633f9b1a41e1d3a011aa1773f5e842802809ee85bedc8ae9 +size 3306259904 diff --git a/DAFT-Qwen3-4B-Instruct-2507.Q8_0.gguf b/DAFT-Qwen3-4B-Instruct-2507.Q8_0.gguf new file mode 100644 index 0000000..8d3ef6e --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2cca9179cb998cefb1f5561395cdac989b1f6262f5108f3ec4fa36f34935ce8 +size 4280403904 diff --git a/DAFT-Qwen3-4B-Instruct-2507.f16.gguf b/DAFT-Qwen3-4B-Instruct-2507.f16.gguf new file mode 100644 index 0000000..8ce4378 --- /dev/null +++ b/DAFT-Qwen3-4B-Instruct-2507.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805ec38a0f3eccfc476e79151d70018b9511ae0dc044df318abec8711d189b08 +size 8051283904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bfc013d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: aasim-m/DAFT-Qwen3-4B-Instruct-2507 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aasim-m/DAFT-Qwen3-4B-Instruct-2507 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DAFT-Qwen3-4B-Instruct-2507-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/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DAFT-Qwen3-4B-Instruct-2507-GGUF/resolve/main/DAFT-Qwen3-4B-Instruct-2507.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. + +