commit 6bbded29445b11e89170713f13603f0eb8c1e279 Author: ModelHub XC Date: Mon Apr 27 19:40:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sphinx_qwen3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..503d101 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +sphinx_qwen3-8b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sphinx_qwen3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4cdad86 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: xashru/sphinx_qwen3-8b +datasets: +- xashru/sphinx +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xashru/sphinx_qwen3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sphinx_qwen3-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/sphinx_qwen3-8b-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/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sphinx_qwen3-8b-GGUF/resolve/main/sphinx_qwen3-8b.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. + + diff --git a/sphinx_qwen3-8b.IQ4_XS.gguf b/sphinx_qwen3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..d00ab1b --- /dev/null +++ b/sphinx_qwen3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d3556b392c0925e0838bbda307f2993bb978dbf956d8693f2e2b19a0aed3bf +size 4593298432 diff --git a/sphinx_qwen3-8b.Q2_K.gguf b/sphinx_qwen3-8b.Q2_K.gguf new file mode 100644 index 0000000..d5f7037 --- /dev/null +++ b/sphinx_qwen3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be41fa7bfab00e136df88958c060af236ffaeb463c0435cbcc77b3c16ec135e +size 3281734656 diff --git a/sphinx_qwen3-8b.Q3_K_L.gguf b/sphinx_qwen3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..b01bd3d --- /dev/null +++ b/sphinx_qwen3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5622060aa0999600b008a51b6d8a1854ac3a7d79e4c98285a80ff157b92e31e9 +size 4431395840 diff --git a/sphinx_qwen3-8b.Q3_K_M.gguf b/sphinx_qwen3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..9763020 --- /dev/null +++ b/sphinx_qwen3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f355af139cdbd3dd7d6e9ae2b72dbf2e04c86fbdc8421741d038962ba48cbf36 +size 4124163072 diff --git a/sphinx_qwen3-8b.Q3_K_S.gguf b/sphinx_qwen3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..d3b44eb --- /dev/null +++ b/sphinx_qwen3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f438fe4a4219f1a48f6fa4674fea8e9270f12aa6c270b7c7929eea5e2d0e76f +size 3769613312 diff --git a/sphinx_qwen3-8b.Q4_K_M.gguf b/sphinx_qwen3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..8058cd7 --- /dev/null +++ b/sphinx_qwen3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6283e477ce5cdb6f2738a078999b79702da83132a288d55174c2a6849ac118c4 +size 5027785728 diff --git a/sphinx_qwen3-8b.Q4_K_S.gguf b/sphinx_qwen3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..9fa0789 --- /dev/null +++ b/sphinx_qwen3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd33ce404b24324cc5d9b48773cb8b6fea99373fe8e1056c20ec5efd82950a5 +size 4802014208 diff --git a/sphinx_qwen3-8b.Q5_K_M.gguf b/sphinx_qwen3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..807b94b --- /dev/null +++ b/sphinx_qwen3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a539c7cc85fb03915b9b70768e2ddf2ff55e2977e917a195c9086e3e88acdaeb +size 5851114496 diff --git a/sphinx_qwen3-8b.Q5_K_S.gguf b/sphinx_qwen3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..b498bb0 --- /dev/null +++ b/sphinx_qwen3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fc2d2b12fdc346a92c2a3205c43c2d3ddddd01ea8f80aaeb85f7e383b098f5 +size 5720763392 diff --git a/sphinx_qwen3-8b.Q6_K.gguf b/sphinx_qwen3-8b.Q6_K.gguf new file mode 100644 index 0000000..64e0b1e --- /dev/null +++ b/sphinx_qwen3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9278cecb86b98a5996dff85e19a7313776d2cba741be01abcfc423d6781cae22 +size 6725901312 diff --git a/sphinx_qwen3-8b.Q8_0.gguf b/sphinx_qwen3-8b.Q8_0.gguf new file mode 100644 index 0000000..145a9e8 --- /dev/null +++ b/sphinx_qwen3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc21f3b95b86f5b8a8e51a74a6dec8b7cc16bdbb29b2d08ba4eb693b95815c1 +size 8709520384 diff --git a/sphinx_qwen3-8b.f16.gguf b/sphinx_qwen3-8b.f16.gguf new file mode 100644 index 0000000..0d91038 --- /dev/null +++ b/sphinx_qwen3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df803a2f8cecb99d418a3199af1771611b886f727634618302fc14d3fc27dbc +size 16388045824 diff --git a/sphinx_qwen3-8b.mmproj-Q8_0.gguf b/sphinx_qwen3-8b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..dca1c19 --- /dev/null +++ b/sphinx_qwen3-8b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404772deb00727e91a9ce9b60528605a6b6c2251539c2e17beb8513fde6bbd89 +size 752290240 diff --git a/sphinx_qwen3-8b.mmproj-f16.gguf b/sphinx_qwen3-8b.mmproj-f16.gguf new file mode 100644 index 0000000..5982c01 --- /dev/null +++ b/sphinx_qwen3-8b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d77275041cae412e44d8d7b7aff969d6b96953934e231097be463500c08251 +size 1159030336