commit ed1eca873c3a06d0366924e9e0f6dcd91653b5e9 Author: ModelHub XC Date: Fri Oct 16 11:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3120569 --- /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.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MAI-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen5-MAI-gemma-2-9B.IQ4_XS.gguf b/MT3-Gen5-MAI-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..12d4d08 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200b5cfca7723a3354dfd0ab4748438b19511aa44e22e6405349fbd9d7df5c31 +size 5223171968 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q2_K.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..c51d02c --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691deb989ab10fbf3a78dcf7e8b9649c7b78b78e52261ae3426b49f9a146b7df +size 3805398912 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q3_K_L.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..f8a8b0b --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826f82393b54e6a3164df5bf11652ff464ca9474e22b311c9353eed963385924 +size 5132453760 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q3_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..5de3dc3 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86327323daf7ce5d76f7f6af597534670c66b6ab552eec9316ee07ce819ce927 +size 4761782144 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q3_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..9fe3ea8 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ced22a8f1264fb15c3064c8644b4f7e4db8bc6cf13fd0eb410617e302ce056 +size 4337665920 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q4_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..494f433 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9cc0aa5a43ea89f507aee6fd0a602e3777f5c1c3be72eea5e407a84b99b92ff +size 5761058688 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q4_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..c3bf352 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dcd47705699d8e39032315dbbffc4c5f57721c13ea68d62455a7b3c41b89053 +size 5478926208 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q5_K_M.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..9c80058 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc952c4a80c20b9a5fbe4c32ef50f2a527ecc7d21d6a289e2a437a60c8a75a7 +size 6647367552 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q5_K_S.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..0562891 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34ec9a360990e10535bf608148479cc87622ed87d2fcb55d7d38e318d72d672 +size 6483593088 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q6_K.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..b6a937d --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9454890d9fc4869bdb247a9f0a316cb2f4b9a953872b99d09ec2d1ef73c967dc +size 7589070720 diff --git a/MT3-Gen5-MAI-gemma-2-9B.Q8_0.gguf b/MT3-Gen5-MAI-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..66320ea --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07476c47c1e25516de9870c24a1286b917cc8cf9c3992b295b1a3369a8c9634b +size 9827149696 diff --git a/MT3-Gen5-MAI-gemma-2-9B.f16.gguf b/MT3-Gen5-MAI-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..6ed9251 --- /dev/null +++ b/MT3-Gen5-MAI-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62b7ba230847a6de462f7c7b2bed5f2ab8e0a184fb690d72c34fd72b49d7976 +size 18490681216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..453ffcc --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen5-MAI-gemma-2-9B +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 + + +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-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MAI-gemma-2-9B-GGUF/resolve/main/MT3-Gen5-MAI-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. + +