commit 3b746e029eeb7dbc4a72992e3ca145696bdd5542 Author: ModelHub XC Date: Thu Sep 3 21:34:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5ec56a1 --- /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 +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.IQ4_XS.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.IQ4_XS.gguf new file mode 100644 index 0000000..5a11d29 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9404a79dd23cbb3e544e00e5bc054cc07db9d1f0ec4045741c3722412ba98c29 +size 5223171936 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q2_K.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q2_K.gguf new file mode 100644 index 0000000..a7cbb18 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fb2555f85e0ff5fde0069c166319c5b5d16f91f3532a03d393fbbdbf05da32 +size 3805398880 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_L.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_L.gguf new file mode 100644 index 0000000..4a968a3 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172d39ff1394fd713c22c1585ea50cbb45a81187b827ce1a16e90d52fca3c067 +size 5132453728 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_M.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_M.gguf new file mode 100644 index 0000000..830e3bf --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7c53ad9da2030a2aafa046acb903e3228095cb596826bde166539a0ae2f249 +size 4761782112 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_S.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_S.gguf new file mode 100644 index 0000000..140ddf0 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cfd654793e1dc9213d1223c71fc1917e8f6f84365e791b41249fffac811333 +size 4337665888 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_M.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_M.gguf new file mode 100644 index 0000000..9a07bf6 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57cd59f28e46b4807b693bdf1b0904ebf7fddc3f5c79a71ab1174bf234d7bcd6 +size 5761058656 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_S.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_S.gguf new file mode 100644 index 0000000..56fb27e --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8e1f83db498e351d06ec94b7b8a0861278f05c93b2650a0f0f8b06abcf66af +size 5478926176 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_M.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_M.gguf new file mode 100644 index 0000000..d566ad0 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6853fccaa42c5b19989fcb4ed60a966c87fdf00adc42be04a7038605403cff75 +size 6647367520 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_S.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_S.gguf new file mode 100644 index 0000000..d5c82d1 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3cf0786cb49a05b9b18d89f80262b88b80621a3d3ca3684ffe6f6afd34c12e +size 6483593056 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q6_K.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q6_K.gguf new file mode 100644 index 0000000..8ac8295 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8098ca7b95d3c39388b85d8656752d5cb653777954a95003436b75e4286dea +size 7589070688 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q8_0.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q8_0.gguf new file mode 100644 index 0000000..494ecd8 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87a7087491ca29314b9a63771a732a7073b496da0615269e803da9faf7f27bb +size 9827149664 diff --git a/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.f16.gguf b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.f16.gguf new file mode 100644 index 0000000..3268507 --- /dev/null +++ b/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d777f5080373e965922375689f891393c6fd3cfb57c0f3995842c7bb8a15ce4e +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3d178c --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: zelk12/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-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/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B-GGUF/resolve/main/MT-Gen5-MM-gemma-2-MT4g2MT5g4-9B.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. + +