commit 51eecd7099a6c06b6dc9012874b0e80a1dab1cf7 Author: ModelHub XC Date: Wed Apr 29 04:03:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f84838e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +MT4-Gen2-MAMU-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen2-MAMU-gemma-2-9B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT4-Gen2-MAMU-gemma-2-9B.IQ4_XS.gguf b/MT4-Gen2-MAMU-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..503fc99 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9013a5656e1ef5fcde7dd5d90dd3875f3b0dec5c727e8526a7894720a8b142 +size 5223172000 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q2_K.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..8c01d79 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a4283d9216071237da45dcd0e723ebd5b97f613f265dff106dd2158a08cc5b +size 3805398944 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_L.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..9aadf08 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99c23e664dd2c31b521634aa12ba35eed3e5ad76f4918781fe1c71cf51a3ced +size 5132453792 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_M.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..5b496b1 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a7a299835e61549e16129033fc3bdf77d7ba9ce43e8ee690046a8b42109b25 +size 4761782176 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_S.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..ce42b9e --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8dcc83fbacabdf2dc4de07c8726a28251e6b6263f568aaf15d23b183134abb +size 4337665952 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q4_0_4_4.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q4_0_4_4.gguf new file mode 100644 index 0000000..04ae54a --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b5034b241baeef7c4d75d2f2ae39d650b709d86845edf25cba5a9cc9bd20cb +size 5443143584 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_M.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..1435e37 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d16e55a32c07f8f0adf4e8410759b164eb7be42636a986c00fb0e62b79a135ba +size 5761058720 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_S.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..4ed6b69 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731712f9083edd90307b335c485ffcb533aa664a03d7c829882b56d87e890d72 +size 5478926240 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_M.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..72720ab --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b5611129069590173b0c22875291f2a9b1bec06018fc53405738736a770eac +size 6647367584 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_S.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..b5cfe7c --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd03ff1c58305a0142728fe7d54306f48509e755601c51ff7d5a272d8cb45839 +size 6483593120 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q6_K.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..5fe1edc --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8400f28f42eea3beb88f89ed10782ccd514a9321e4ddfa856feadda8617eb4e7 +size 7589070752 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.Q8_0.gguf b/MT4-Gen2-MAMU-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..c80f544 --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d15ea798de4eda82c2e4989f1e8815bf7e24b34e0bb34f8137d3e1d334f318 +size 9827149728 diff --git a/MT4-Gen2-MAMU-gemma-2-9B.f16.gguf b/MT4-Gen2-MAMU-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..d4abbec --- /dev/null +++ b/MT4-Gen2-MAMU-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba37fc854c4331673206e9173b65d1fa5abdc211711b15c141a3ddcee08634f +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ca1e34 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: zelk12/MT4-Gen2-MAMU-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT4-Gen2-MAMU-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/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen2-MAMU-gemma-2-9B-GGUF/resolve/main/MT4-Gen2-MAMU-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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +