commit 0bf0abc11d9a22a45a1666a24e5f0b43db77fd5c Author: ModelHub XC Date: Wed Jul 22 20:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..296304a --- /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-Instruct-2507-MPOA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-MPOA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Instruct-2507-MPOA.IQ4_XS.gguf b/Qwen3-4B-Instruct-2507-MPOA.IQ4_XS.gguf new file mode 100644 index 0000000..3c9942e --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3faafd954383d34b546802aa79e4bf3ad9a6b8afe4c43b2e767064a4755da7 +size 2286315328 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q2_K.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q2_K.gguf new file mode 100644 index 0000000..2b828bf --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11cc5236a22dd3827f55b54837b41da9cabaa74c2ed7fb9621241a012fa16b45 +size 1669498688 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q3_K_L.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_L.gguf new file mode 100644 index 0000000..4e52645 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61dc0c71f957faf3055703aa95dcfc8b3a05784566c0bff83bcac930ed68454 +size 2239784768 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q3_K_M.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_M.gguf new file mode 100644 index 0000000..01b22af --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701db53157b492d83fa7f2c21df99b73bd437b38455db89fbcf411b55647ff2e +size 2075617088 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q3_K_S.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_S.gguf new file mode 100644 index 0000000..e3bf8ca --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7967192c520db0fa4b5b7bf8f2b66755593a8858f9d9d7fd78589f72d21c50 +size 1886996288 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q4_K_M.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q4_K_M.gguf new file mode 100644 index 0000000..6eb9d54 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf1ef900e8e0e01ac8254f49a377ca17db623ffc31dd21e9a20a9261c45768f +size 2497279808 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q4_K_S.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q4_K_S.gguf new file mode 100644 index 0000000..e546fbd --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bb9a4487855298e6ab67887cd9acc0814b4462bc0587062ced3f5d71df598c +size 2383308608 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q5_K_M.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q5_K_M.gguf new file mode 100644 index 0000000..a738edf --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24732b5b543122c7684829ded43ff94f136623a72cfcb19407e4167e3c5f7532 +size 2889512768 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q5_K_S.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q5_K_S.gguf new file mode 100644 index 0000000..c65036f --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c14b7f23ffe0b2d5988b1c14975e749a7606cfafb79b70548b81a08b6a4a7d +size 2823710528 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q6_K.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q6_K.gguf new file mode 100644 index 0000000..029f0e1 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58d8b388880524129517149ca62f838f001dbb362d62d35aa2f33879e53dd3d +size 3306260288 diff --git a/Qwen3-4B-Instruct-2507-MPOA.Q8_0.gguf b/Qwen3-4B-Instruct-2507-MPOA.Q8_0.gguf new file mode 100644 index 0000000..50e74e7 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eea3d91ac6a392d6a146a3125d619d84c33e0e14afa8bc099a9018a1dfc7fa3 +size 4280404288 diff --git a/Qwen3-4B-Instruct-2507-MPOA.f16.gguf b/Qwen3-4B-Instruct-2507-MPOA.f16.gguf new file mode 100644 index 0000000..3684d9e --- /dev/null +++ b/Qwen3-4B-Instruct-2507-MPOA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5259f8d04ce64142883d0ff44ef6e441416121774eb811e560f719ef093b623a +size 8051284288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..99fd1b6 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: YanLabs/Qwen3-4B-Instruct-2507-MPOA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/YanLabs/Qwen3-4B-Instruct-2507-MPOA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Instruct-2507-MPOA-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-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/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-MPOA-GGUF/resolve/main/Qwen3-4B-Instruct-2507-MPOA.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. + +