commit 0b8af9ba646c1d86321dd7b79a97c8dd13d68242 Author: ModelHub XC Date: Fri Jun 26 08:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9dc6bfd --- /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 +MT-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-gemma-2-9B.IQ4_XS.gguf b/MT-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..29875ec --- /dev/null +++ b/MT-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a242734ce00ce8f44130af3f885f77a48748ebba9c7de94758a9f382921092 +size 5223171872 diff --git a/MT-gemma-2-9B.Q2_K.gguf b/MT-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..ebfd4f1 --- /dev/null +++ b/MT-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6110efb36753406cf0dec9d5ea2d04ad4944e95e5be88113291e5a983090161 +size 3805398816 diff --git a/MT-gemma-2-9B.Q3_K_L.gguf b/MT-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..ed1a6fd --- /dev/null +++ b/MT-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c518d3a6af520bac18cb25ab82c5a2fae1e8b1512e4bad3ae8834099a974ef8 +size 5132453664 diff --git a/MT-gemma-2-9B.Q3_K_M.gguf b/MT-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..5f29232 --- /dev/null +++ b/MT-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f2e87d8c0263717a67895112bbec7bbdb88c9fe1842c010ea1c1f4f7c1702b +size 4761782048 diff --git a/MT-gemma-2-9B.Q3_K_S.gguf b/MT-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..689899b --- /dev/null +++ b/MT-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec118ff892eab02ae53c40ab540c1fdf88e2ea14dfc0aac18194b68147ebee2e +size 4337665824 diff --git a/MT-gemma-2-9B.Q4_K_M.gguf b/MT-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..59fb185 --- /dev/null +++ b/MT-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0161c364a2a67ac118c11acc9b9f80bfb9bbc93fb77e449fda96f355cec40a +size 5761058592 diff --git a/MT-gemma-2-9B.Q4_K_S.gguf b/MT-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..c74e25a --- /dev/null +++ b/MT-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b034a83bf2d15c10089e7e14314b3944cca6ec72947b27dfb8b2ff52e81a90ea +size 5478926112 diff --git a/MT-gemma-2-9B.Q5_K_M.gguf b/MT-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..a124c08 --- /dev/null +++ b/MT-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba250d127e622ceca4e8bfa462fb5c5faae1da90778968c69103c720641cef81 +size 6647367456 diff --git a/MT-gemma-2-9B.Q5_K_S.gguf b/MT-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..6aa9883 --- /dev/null +++ b/MT-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e626cb251d329bc30ffa472662865a09ef808d7337bce4bafb70a658a1b1fd9 +size 6483592992 diff --git a/MT-gemma-2-9B.Q6_K.gguf b/MT-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..fdd0492 --- /dev/null +++ b/MT-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e389117d8b3f4441950c7a5f49d44b3ea3c4fcecc68d5c08571c5e2a91e5a947 +size 7589070624 diff --git a/MT-gemma-2-9B.Q8_0.gguf b/MT-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..1fe79fc --- /dev/null +++ b/MT-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cae8077610bfdab22d5726343560e769918f943ba803690cfd5120172267fba +size 9827149600 diff --git a/MT-gemma-2-9B.f16.gguf b/MT-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..f5db50c --- /dev/null +++ b/MT-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f589d4c113f93d1a6342514aa003fafa3338effa76fab66f55076234a4a685a +size 18490681120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b3fcdb --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT-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/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT-gemma-2-9B-GGUF/resolve/main/MT-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. + +