commit d3675a2deb57dff7716a83d37ec1c0b05743c042 Author: ModelHub XC Date: Wed May 20 17:13:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT2-Gen10-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c4f0df --- /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 +MT2-Gen10-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen10-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT2-Gen10-gemma-2-9B.IQ4_XS.gguf b/MT2-Gen10-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..8d7c6f0 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b631f15ac1abdf39d18ce9a86b543d3f611b815f08e49a39e7447f44b8ba36 +size 5223172928 diff --git a/MT2-Gen10-gemma-2-9B.Q2_K.gguf b/MT2-Gen10-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..087e24b --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7497809cbc71a95b3eb5469f35c07b8e535001f48c60fa2568e4a008d2288b +size 3805399872 diff --git a/MT2-Gen10-gemma-2-9B.Q3_K_L.gguf b/MT2-Gen10-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..cffe233 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1967181593566926317fd2e57aa4e425984845bb5b52495faaf54030b189434 +size 5132454720 diff --git a/MT2-Gen10-gemma-2-9B.Q3_K_M.gguf b/MT2-Gen10-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..becec38 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519c1abaa135b9a5290373c7089fc03d9bfec988b93caa5285c92e4f6757c16a +size 4761783104 diff --git a/MT2-Gen10-gemma-2-9B.Q3_K_S.gguf b/MT2-Gen10-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..90aab5a --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847622088910f12dfbb23d54dfe3cbf5cec7f74d32fb1841a4c31bf48c6bb0b8 +size 4337666880 diff --git a/MT2-Gen10-gemma-2-9B.Q4_K_M.gguf b/MT2-Gen10-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..d1ae599 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c865e7ebc3ec6c5627c6ba49b119c0a6072febfc654b8a53eb3ce0a7de8ba90 +size 5761059648 diff --git a/MT2-Gen10-gemma-2-9B.Q4_K_S.gguf b/MT2-Gen10-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..4c99866 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdffb561666b7d9967c6b68aad65c50335f1d8a1bbb3ad199b885e496482247 +size 5478927168 diff --git a/MT2-Gen10-gemma-2-9B.Q5_K_M.gguf b/MT2-Gen10-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..c06b179 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d874dc8d1f24c8468f0b0f0b7314d525b3187d493490d78eb8e535703bba57dd +size 6647368512 diff --git a/MT2-Gen10-gemma-2-9B.Q5_K_S.gguf b/MT2-Gen10-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..407379b --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f771270bbcb0e490b0484bf35a2d07d83daf15ba9142b0baab6a913db206b34d +size 6483594048 diff --git a/MT2-Gen10-gemma-2-9B.Q6_K.gguf b/MT2-Gen10-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..5f5ea1f --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712345efe3993963304563184fca89878eef9b4f9d33688e032d37493bd67620 +size 7589071680 diff --git a/MT2-Gen10-gemma-2-9B.Q8_0.gguf b/MT2-Gen10-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..0c68ae9 --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e0e319bd795443d36f72bd1863e587398240c2a074914d0819313a9589315f +size 9827150656 diff --git a/MT2-Gen10-gemma-2-9B.f16.gguf b/MT2-Gen10-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..d7030ae --- /dev/null +++ b/MT2-Gen10-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c011de6802454e81af368c60ceb25a3526df7eb429aa3149ce0cd4346b8f2bd9 +size 18490682176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e59676c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: zelk12/MT2-Gen10-gemma-2-9B +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT2-Gen10-gemma-2-9B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT2-Gen10-gemma-2-9B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-i1-GGUF +## 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/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen10-gemma-2-9B-GGUF/resolve/main/MT2-Gen10-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. + +