commit c3d2c67c8b456797c6ec4b84008c517b11802be0 Author: ModelHub XC Date: Fri Oct 16 13:30:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0cbaabe --- /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-MMGBMU-gemma-2-9B_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MMGBMU-gemma-2-9B_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.IQ4_XS.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.IQ4_XS.gguf new file mode 100644 index 0000000..3c9dc8f --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c33b21b014dad74a943e6dfc539b9691bc194e0eded95988ae3b3825457ed4 +size 5223172000 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q2_K.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q2_K.gguf new file mode 100644 index 0000000..b352cdd --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9857ab2af7d0c2bf96c537b6c711bc11b2140251314a7886344050a3333f7c12 +size 3805398944 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_L.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_L.gguf new file mode 100644 index 0000000..584e550 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc48f85de4ec3ee30bf983b75e9cbf74c500dc2ddf9bc01902b71cc9d04636f +size 5132453792 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_M.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_M.gguf new file mode 100644 index 0000000..9669ea6 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e840a42dad8dc1b67fc4ccfb6beaec454e5ff957969c984446d19dfb1f3e8ed +size 4761782176 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_S.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_S.gguf new file mode 100644 index 0000000..efc918f --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cb2a079f40f9f1fe7ef738f2efea4b447df338e6851f2341a4c6617f1e9c8e +size 4337665952 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_M.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_M.gguf new file mode 100644 index 0000000..f48a2c0 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88bfe928830eea515a52078d0a6d1db03fab8357bdaf0bb77f34b34e1442f9a +size 5761058720 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_S.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_S.gguf new file mode 100644 index 0000000..cb46a2a --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f985db24bdcd74caa46309963a8880c1c564651cd5350453c217a26511c9dcad +size 5478926240 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_M.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_M.gguf new file mode 100644 index 0000000..be7f121 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afcad88d7a88265d60b84819eafb72e21c84bcde68ea78829e29a10c8f869cb +size 6647367584 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_S.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_S.gguf new file mode 100644 index 0000000..bfcf036 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eccbf67dd69415745172cd3d07585d6e0e848ccbb229cb2999541cf7f96aeb3 +size 6483593120 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q6_K.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q6_K.gguf new file mode 100644 index 0000000..fa09215 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a6c4c135a354df363e22a2f5833f43d176d5b356e40556ee3476e12ed1b14b +size 7589070752 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q8_0.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q8_0.gguf new file mode 100644 index 0000000..5acb1ed --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35a3b1bd5bed2e7f07c92d22cebf9b98a14da9a0e8aadc579201e871e2292e0 +size 9827149728 diff --git a/MT3-Gen5-MMGBMU-gemma-2-9B_v1.f16.gguf b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.f16.gguf new file mode 100644 index 0000000..e6e4695 --- /dev/null +++ b/MT3-Gen5-MMGBMU-gemma-2-9B_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e455aa2c0ff7872f936626905c94430b3a30da661280b6e81df037675d16406 +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b6174b --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen5-MMGBMU-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-MMGBMU-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-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-gemma-2-9B_v1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MMGBMU-gemma-2-9B_v1-GGUF/resolve/main/MT3-Gen5-MMGBMU-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. + +