commit a376ed631ae3ca42b991a2a03c68fbebaf664c8f Author: ModelHub XC Date: Fri Jun 26 13:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae0987c --- /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-Gen3-GMA-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen3-GMA-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen3-GMA-gemma-2-9B.IQ4_XS.gguf b/MT3-Gen3-GMA-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..5c5418b --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8f67014791e6871603f9e0702702a224541872249e8b484df3c77e0595234f +size 5223172000 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q2_K.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..b2c813b --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6059d7626e1e042dd02256b13797365b31cdd399ac7345228787585ea938c9e0 +size 3805398944 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q3_K_L.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..d3f8bb6 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6de024691bce4a20b84100a3934196e50003cc4908d3aee4ee53661012d565 +size 5132453792 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q3_K_M.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..08faba9 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cfa461f5af73d97430c5df1e8461b0557516203fcb762e52d8874e1e245893 +size 4761782176 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q3_K_S.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..06aecc3 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1e8a10b50342e002df0c253d05a54213ec231d3113202ddd25399eb57bcde1 +size 4337665952 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q4_K_M.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..c335dd4 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427fc8798dd9fce1a8d21a4fc32b67cb698d1d85a0a7436e0adeebd77cacaa44 +size 5761058720 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q4_K_S.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..f1466f0 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54365fc932a0857f02ab72ee62684348de25e0c34d35d847e7680119d334b65c +size 5478926240 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q5_K_M.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..af0fc48 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb84773e58c71775740d5e147e368a18545599a36a955c8f24a938111d2cd5a1 +size 6647367584 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q5_K_S.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..2e0c3e8 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be049f2c1e9bc62ab91f406a0f211906f30cab986002dbfb3c037514da4d2f32 +size 6483593120 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q6_K.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..6888eb3 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7b92b9de62a81a3de0584a7d5cbc2862a845ccca2d102fe29eb91094f19af8 +size 7589070752 diff --git a/MT3-Gen3-GMA-gemma-2-9B.Q8_0.gguf b/MT3-Gen3-GMA-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..66d3bf9 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec6b2322b5eb5f9eb68dce5a1f7b4606c65cb670566d53aeb02a1e8b4bfb2134 +size 9827149728 diff --git a/MT3-Gen3-GMA-gemma-2-9B.f16.gguf b/MT3-Gen3-GMA-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..5a68ea9 --- /dev/null +++ b/MT3-Gen3-GMA-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061b28d75e2753856214f357296b1b1633e6186b9e036f18ca724a9a46376b1d +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d90147 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: zelk12/MT3-Gen3-GMA-gemma-2-9B_ANY_MERGE_MODELS_DELETED +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen3-GMA-gemma-2-9B_ANY_MERGE_MODELS_DELETED + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT3-Gen3-GMA-gemma-2-9B-GGUF).*** + +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-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen3-GMA-gemma-2-9B-GGUF/resolve/main/MT3-Gen3-GMA-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. + +