commit 5441b41204aec953dfb3b552d58be09fb34595df Author: ModelHub XC Date: Wed Jul 1 19:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f91bec1 --- /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-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.IQ4_XS.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..fec6145 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918a44ed1607b697addfaa551a91b2b5d0796570ce37f37fb53413e931ac9753 +size 5223172096 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q2_K.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q2_K.gguf new file mode 100644 index 0000000..d9ac695 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6547dbf0ec92b88f7710157b16ab615efe6beb89c391d246aaa34984b4f50316 +size 3805399040 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_L.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..a5cd221 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf034879392083a886c8b7dee338cd454ed352404e58135cf8eea180f429144 +size 5132453888 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_M.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..108a745 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bc6ceabb77946971df443953a95f6979894efdb0d8f07442da289642923890 +size 4761782272 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_S.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..00294c7 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9af40007554b997f881f4d6189c72f2aff32e9f2cc678625fbb43d955a6d3a04 +size 4337666048 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_M.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..6d2412f --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ef4af2369a03739f310cd8d517aa284371c50cb6949ce2c112df39c7856394 +size 5761058816 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_S.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..a1a7491 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0427b5abb1ec13cf2de2ec8ad86ae311c90a6a11d1b4c4d7127eadf1ec532b7 +size 5478926336 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_M.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..95e83de --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b49fbd14cf0f3ad6644e71d6391af23e42162134721abbfbab437781e44c387 +size 6647367680 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_S.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..7196cb6 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe00b1f7219b64a527d57e7eea49eb8ba4ff713792bbdae964b6629bdf9a0e9 +size 6483593216 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q6_K.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q6_K.gguf new file mode 100644 index 0000000..e363bc8 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c21e77dd000dd3aebd48ab13bf23c076b287f19f418871c658eaa0459aaa485 +size 7589070848 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q8_0.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q8_0.gguf new file mode 100644 index 0000000..5844d71 --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8464a54011221f9b3c3c4e1ded9e30ec84bc22f9313f108f05fdf28f6f2dc49 +size 9827149824 diff --git a/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.f16.gguf b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.f16.gguf new file mode 100644 index 0000000..2dd9dcb --- /dev/null +++ b/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad01eb85e088acdb912c5f1adc1b3bc15ed74a488fee2526569092a2ee58583d +size 18490681344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd9abc3 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B + + +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-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B-GGUF/resolve/main/MT3-Gen4-MA-gemma-2-Sv1IBTMT2g2-9B.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. + +