commit 6de376623901712a07a14e53f91abf5fcd8df077 Author: ModelHub XC Date: Sat May 9 14:29:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3OIE-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4a20b2 --- /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 +Qwen3OIE-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3OIE-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3OIE-8B.IQ4_XS.gguf b/Qwen3OIE-8B.IQ4_XS.gguf new file mode 100644 index 0000000..2925eab --- /dev/null +++ b/Qwen3OIE-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb791a67bcec563297a52dda1ada4629d8aae740732c96f5b2042474041c2d5 +size 4593297024 diff --git a/Qwen3OIE-8B.Q2_K.gguf b/Qwen3OIE-8B.Q2_K.gguf new file mode 100644 index 0000000..9df20f9 --- /dev/null +++ b/Qwen3OIE-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb54138127c2bb6dc876d6f8c8120daecbd66fdc6e9ad7acd1788afd17120b4 +size 3281733248 diff --git a/Qwen3OIE-8B.Q3_K_L.gguf b/Qwen3OIE-8B.Q3_K_L.gguf new file mode 100644 index 0000000..dd1fc78 --- /dev/null +++ b/Qwen3OIE-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:498138b67e483d973c38bc51e0d19df89b1ea52129a9d3bbc40d4a3db2912214 +size 4431394432 diff --git a/Qwen3OIE-8B.Q3_K_M.gguf b/Qwen3OIE-8B.Q3_K_M.gguf new file mode 100644 index 0000000..2f2d2bf --- /dev/null +++ b/Qwen3OIE-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c4d0960766ef0ae9b5081e73f0791d745a637924dcd00c9d2eded7ed7a3569 +size 4124161664 diff --git a/Qwen3OIE-8B.Q3_K_S.gguf b/Qwen3OIE-8B.Q3_K_S.gguf new file mode 100644 index 0000000..92edf48 --- /dev/null +++ b/Qwen3OIE-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3256b08a50df5a198b5ded0e4222545c84ddf7801bdc134d71bbbef0d3cf31f2 +size 3769611904 diff --git a/Qwen3OIE-8B.Q4_K_M.gguf b/Qwen3OIE-8B.Q4_K_M.gguf new file mode 100644 index 0000000..353b114 --- /dev/null +++ b/Qwen3OIE-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e6e4b1d33ccc60b26ea393a170303d973e7861c92eec0555a9c3d790d306d6 +size 5027784320 diff --git a/Qwen3OIE-8B.Q4_K_S.gguf b/Qwen3OIE-8B.Q4_K_S.gguf new file mode 100644 index 0000000..dbc9d82 --- /dev/null +++ b/Qwen3OIE-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808636421ed6aa59299f4f1ee2d64338f9b3d9327665b3e67069c1a319f2a9f0 +size 4802012800 diff --git a/Qwen3OIE-8B.Q5_K_M.gguf b/Qwen3OIE-8B.Q5_K_M.gguf new file mode 100644 index 0000000..1ab5978 --- /dev/null +++ b/Qwen3OIE-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72dbc5e0c099287ba21205ed5540ec34ba480cdb705db60d24feb926ca6af6e +size 5851113088 diff --git a/Qwen3OIE-8B.Q5_K_S.gguf b/Qwen3OIE-8B.Q5_K_S.gguf new file mode 100644 index 0000000..a7e65e8 --- /dev/null +++ b/Qwen3OIE-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97cac0c49c8bb4d43591d0e7470181d0b84b995d6886a952f6b256c2486f11f +size 5720761984 diff --git a/Qwen3OIE-8B.Q6_K.gguf b/Qwen3OIE-8B.Q6_K.gguf new file mode 100644 index 0000000..39a0bf3 --- /dev/null +++ b/Qwen3OIE-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46fba8f0c539152762b2216e3bf1511c4f12b924c94a2df9d226c129aba3952 +size 6725899904 diff --git a/Qwen3OIE-8B.Q8_0.gguf b/Qwen3OIE-8B.Q8_0.gguf new file mode 100644 index 0000000..e99acfa --- /dev/null +++ b/Qwen3OIE-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259851cc9adabe1ec918330e9606077f08a052ca3ec7681db478a3f86ad3c11e +size 8709518976 diff --git a/Qwen3OIE-8B.f16.gguf b/Qwen3OIE-8B.f16.gguf new file mode 100644 index 0000000..6c02e60 --- /dev/null +++ b/Qwen3OIE-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbd3fb0c42d37054aa263d49b7e7f32018c5b9c6c811a097c5250846416a86e +size 16388044416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2989a0b --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: bratao/Qwen3OIE-8B +datasets: +- train_dataset_updated.jsonl +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/bratao/Qwen3OIE-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3OIE-8B-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/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3OIE-8B-GGUF/resolve/main/Qwen3OIE-8B.f16.gguf) | f16 | 16.5 | 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. + +