commit b9e74eadd8a59d0a90c6df6d6d46608d0a5641a0 Author: ModelHub XC Date: Tue Oct 20 14:12:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3972a5 --- /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 +MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.IQ4_XS.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.IQ4_XS.gguf new file mode 100644 index 0000000..27a6c58 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99417ca5ee0ed0b93facb8eedc13276ce650c4997e7ce1d3a96cd8383cf9c4f0 +size 5223172032 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q2_K.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q2_K.gguf new file mode 100644 index 0000000..39f2cf1 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ebc99c3fdb0ab4640b625c954d558b8dd3a657bbb2ce7bc754fa0e551f07459 +size 3805398976 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_L.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_L.gguf new file mode 100644 index 0000000..6edc016 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081136b0ce35af985187b5e2ba10e96b100b925e8d13be7a3012b42a71d80907 +size 5132453824 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_M.gguf new file mode 100644 index 0000000..938ecab --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2d212faa254364be3c152f580e687d3b89e541a989434cfd21dd9a91dcef30 +size 4761782208 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_S.gguf new file mode 100644 index 0000000..280b2ee --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2134e29215c9ac3b324f098ff5239d12ba6c5805a88da6434e443018cbc87fdf +size 4337665984 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_M.gguf new file mode 100644 index 0000000..ec8dd85 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b273a993107a99c82652371818c9ee670ad0796126b3c769534f27ceaf99ef +size 5761058752 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_S.gguf new file mode 100644 index 0000000..f4b926e --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b226a4074061270db516fa4486b7a75d0a61231bf4acb7b5514d270dedfbfc +size 5478926272 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_M.gguf new file mode 100644 index 0000000..c3df802 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35a382da9a72d7e0a802bf4ee790b7acc564e24c2b218b70c2079264765b313 +size 6647367616 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_S.gguf new file mode 100644 index 0000000..3faff03 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd730c2d9f2efd4149baa048f510445b0251570565fe3f327f0dec1334e0b711 +size 6483593152 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q6_K.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q6_K.gguf new file mode 100644 index 0000000..d9ab006 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641e074fe9306a123171686a54c5ac6d7458f98980c54f0e89b3ff69cba6256d +size 7589070784 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.Q8_0.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.Q8_0.gguf new file mode 100644 index 0000000..5de8b10 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e18b111d0d06b97064ed0eff80f0ca27cc91976cbe6ff34400546c410f1bf95 +size 9827149760 diff --git a/MT3-Gen5-MAI-gemma-2-9B_v1.f16.gguf b/MT3-Gen5-MAI-gemma-2-9B_v1.f16.gguf new file mode 100644 index 0000000..8d024e5 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1abfe489c50e82d5d99b3100035dea2d0fb607222cf50769bde6e688a10a7a +size 18490681280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d962ad5 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen5-MAI-gemma-2-9B_v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen5-MAI-gemma-2-9B_v1 + + +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/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B_v1.f16.gguf) | f16 | 18.6 | 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. + +