commit f8370bab3d6a233842f59672c7526b612d06cf59 Author: ModelHub XC Date: Wed Sep 2 21:58:18 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..4b612f9 --- /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-f16.gguf filter=lfs diff=lfs merge=lfs -text +sphinx-qwen3-8b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sphinx-qwen3-8b.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.Q8_0.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_M.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..ead88f3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: maveryn/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/maveryn/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..2e574c9 --- /dev/null +++ b/sphinx-qwen3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dacf914523be46d87991a2bb616b9381fef5b779f9bf82f42c287d7ecb3341c +size 4593298496 diff --git a/sphinx-qwen3-8b.Q2_K.gguf b/sphinx-qwen3-8b.Q2_K.gguf new file mode 100644 index 0000000..ab5ae97 --- /dev/null +++ b/sphinx-qwen3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100252badcffac69dea9bf7852e8029e181f8d4a526fb4269f7064d89d41f873 +size 3281734720 diff --git a/sphinx-qwen3-8b.Q3_K_L.gguf b/sphinx-qwen3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..b40f103 --- /dev/null +++ b/sphinx-qwen3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c8aa6680078f411ecd595c9ff0f678720397f5fa09ae33a7c242de7907644b +size 4431395904 diff --git a/sphinx-qwen3-8b.Q3_K_M.gguf b/sphinx-qwen3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..679c6b2 --- /dev/null +++ b/sphinx-qwen3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fce4563ff7a03047397ad5a72ee616c031ce4ba3ee2e6bd6c015abf6324dd0d +size 4124163136 diff --git a/sphinx-qwen3-8b.Q3_K_S.gguf b/sphinx-qwen3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..ff3de19 --- /dev/null +++ b/sphinx-qwen3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d65476c09276371c4edd4c4a8c9281f93ad7f737d887cd0ff67381b8b765ff +size 3769613376 diff --git a/sphinx-qwen3-8b.Q4_K_M.gguf b/sphinx-qwen3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..515cfaf --- /dev/null +++ b/sphinx-qwen3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d089056af1d47b2c5bc1ad46270968ddab2b453015e442e750b6803eaf2830 +size 5027785792 diff --git a/sphinx-qwen3-8b.Q4_K_S.gguf b/sphinx-qwen3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..777d20a --- /dev/null +++ b/sphinx-qwen3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2371096cc219ba1626a129a58e623e784dd8da87666485015528f49201e97db +size 4802014272 diff --git a/sphinx-qwen3-8b.Q5_K_M.gguf b/sphinx-qwen3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..d2c9de0 --- /dev/null +++ b/sphinx-qwen3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd035a01e1c55fe548b54785d9e0fbac0221ebb4831f83a708338b79133a5e6 +size 5851114560 diff --git a/sphinx-qwen3-8b.Q5_K_S.gguf b/sphinx-qwen3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..f0a330c --- /dev/null +++ b/sphinx-qwen3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a20085dfacbbdad69276ea526c313dfae1ec42b798af4808a2514bd0640a3fa +size 5720763456 diff --git a/sphinx-qwen3-8b.Q6_K.gguf b/sphinx-qwen3-8b.Q6_K.gguf new file mode 100644 index 0000000..9f49693 --- /dev/null +++ b/sphinx-qwen3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07b9e21f8fcfd2cfb8fc99e4d6bca11cdf7a8c6422844db0487a23d67ba4ea5 +size 6725901376 diff --git a/sphinx-qwen3-8b.Q8_0.gguf b/sphinx-qwen3-8b.Q8_0.gguf new file mode 100644 index 0000000..b2e9232 --- /dev/null +++ b/sphinx-qwen3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fdc4964b3897112b01cae9118a8d5101c27a82050354e0f53068fb61ea2d8f +size 8709520448 diff --git a/sphinx-qwen3-8b.f16.gguf b/sphinx-qwen3-8b.f16.gguf new file mode 100644 index 0000000..c114e35 --- /dev/null +++ b/sphinx-qwen3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a18dd2acf93a47ee4dde6b4d5ed236eed0a2961b6259726d8996ee58396a44d0 +size 16388045888 diff --git a/sphinx-qwen3-8b.mmproj-Q8_0.gguf b/sphinx-qwen3-8b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..961511f --- /dev/null +++ b/sphinx-qwen3-8b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e49db97b41b0f43cd4bf5ccc40cc57623c2f6d390e3d84d6dc704baee1bf2ef +size 752290304 diff --git a/sphinx-qwen3-8b.mmproj-f16.gguf b/sphinx-qwen3-8b.mmproj-f16.gguf new file mode 100644 index 0000000..3aca52f --- /dev/null +++ b/sphinx-qwen3-8b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ee35601a35416d9d721394eb275f96c6cad2f360455558f1a5bafea528636b4 +size 1159030400