commit 246f2ec20eb699e2840c55a9dfb5e8b9aca1ec5b Author: ModelHub XC Date: Sat Oct 10 08:29:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..791c280 --- /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 +MTM-Merge-MMMUBI-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMUBI-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.IQ4_XS.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..4bf8e66 --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24531cb52a759eb06d717850368b8f07c99c2596b8daf843b1cd51f9545fca82 +size 5223171968 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q2_K.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..b892aeb --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b40d62a28aa7852975aa93db74cdd7eff6c4bd7cb16b1b38252506ac0cde64 +size 3805398912 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_L.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..6b9031d --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd08c290bad66b7b9c41ba8b0426013807d4beb1fcd9ead3157b9f60599d687 +size 5132453760 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_M.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..3264b69 --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f01ec32d2c7c88a65a0d610ac68faa4a1d64cdee45ea9ba40ef6b44517300f0 +size 4761782144 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_S.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..d649f23 --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6da7efadca2332a4deed224a8f34d4e85d9564d18f72026e650b465bbf8beb +size 4337665920 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_M.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..6272abd --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa0e27f356439f076ac40b2d40b82f45bea51194e9fd48c1524b802f6e5f1eb +size 5761058688 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_S.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..bd3781b --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680f5bffac2abb165f99c5ce7d3686a22cf37ecc94abd5ac3d1dd668fa6d9ec5 +size 5478926208 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_M.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..d8e4aae --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2247241f268ad3f79407929579f3f55894e687ec2dcba068a7c82c8d8cb98778 +size 6647367552 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_S.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..26dfa5b --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88129e5a7e616d0b452aea789db26eb7dda8484b9806e5066dcfffe4f2ed822c +size 6483593088 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q6_K.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..29b8a79 --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbe9a7fc502472e5174ac48bac7d139b232e9303e26be1126a7cb267fcbc967 +size 7589070720 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.Q8_0.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..b5b01fd --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7134ff608240288529dda85ec1f976fd233b3d60e06592889a9c426dfd08859d +size 9827149696 diff --git a/MTM-Merge-MMMUBI-gemma-2-9B.f16.gguf b/MTM-Merge-MMMUBI-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..6181a5b --- /dev/null +++ b/MTM-Merge-MMMUBI-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88455c6405c0a2e94770df44887584e05260536a5ca6aeaeeed176cf823e8886 +size 18490681216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e749bd --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MTM-Merge-MMMUBI-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MTM-Merge-MMMUBI-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/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMUBI-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMUBI-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. + +