commit 848132845bb57ab41785c5a7c69ea1f9edac08f8 Author: ModelHub XC Date: Tue Jul 7 05:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-GMU-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d0b0293 --- /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-GMU-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-GMU-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-GMU-gemma-2-9B.IQ4_XS.gguf b/MT3-GMU-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..75d8c2b --- /dev/null +++ b/MT3-GMU-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb46cb354d2b1ae90241da79985fddd938a33473c356abd4c6d6b9e4ef23cb1 +size 5223172000 diff --git a/MT3-GMU-gemma-2-9B.Q2_K.gguf b/MT3-GMU-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..9dff4da --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d8407f2ad80dc0ec6c5420f5f36a64073b1f9893f2ab7d7caff5ac7ddffabc +size 3805398944 diff --git a/MT3-GMU-gemma-2-9B.Q3_K_L.gguf b/MT3-GMU-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..7d8c631 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c334ed6bb725498ec1c63f24b770605a0435f7cd6b099200f26b256c0cd42e92 +size 5132453792 diff --git a/MT3-GMU-gemma-2-9B.Q3_K_M.gguf b/MT3-GMU-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..18f6dc4 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043bc16d337915ddd54d1afb054b4b78686d5fe66727894bcca3f1224f1b610b +size 4761782176 diff --git a/MT3-GMU-gemma-2-9B.Q3_K_S.gguf b/MT3-GMU-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..151fbbc --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6e2860bbc734cbb44e00a853cfb6ba56f7598919fece8c9e49277fcc7ff57d +size 4337665952 diff --git a/MT3-GMU-gemma-2-9B.Q4_K_M.gguf b/MT3-GMU-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..e9b647e --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3967ccbf4e8e7958b5849daa79450cab67cc03c955632be85823ca05cdb7205b +size 5761058720 diff --git a/MT3-GMU-gemma-2-9B.Q4_K_S.gguf b/MT3-GMU-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..c1111a6 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a6b30092cc07021557f626efd9d1bfcc24fb1170584cb321a819634bf8aff5 +size 5478926240 diff --git a/MT3-GMU-gemma-2-9B.Q5_K_M.gguf b/MT3-GMU-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..765d797 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc8caef0eb064ce2c235b25d949c4cf15ccec24507f6bafd5e7b56a0352084d +size 6647367584 diff --git a/MT3-GMU-gemma-2-9B.Q5_K_S.gguf b/MT3-GMU-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..3ebba57 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e808cb9029191fc251f3c3528061264212894f516323fe15030f03f4e19ca8 +size 6483593120 diff --git a/MT3-GMU-gemma-2-9B.Q6_K.gguf b/MT3-GMU-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..537c81e --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac904418cc9c98087dea561312c31f49f76d3a56c5d1427bf0d1a8e709fe3cd8 +size 7589070752 diff --git a/MT3-GMU-gemma-2-9B.Q8_0.gguf b/MT3-GMU-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..f439326 --- /dev/null +++ b/MT3-GMU-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:695567f6cf3547e4c8d39a1afcaa0821bed51158a342c92ef6a3e44214d70eaf +size 9827149728 diff --git a/MT3-GMU-gemma-2-9B.f16.gguf b/MT3-GMU-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..7f89c3f --- /dev/null +++ b/MT3-GMU-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffec53e76cee97662e2914571e1bb167b279c35bc0a7ef83220fcd745e98a5c9 +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c923116 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-GMU-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-GMU-gemma-2-9B + + +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-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-GMU-gemma-2-9B-GGUF/resolve/main/MT3-GMU-gemma-2-9B.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. + +