commit c7bf3e3ea578b9fb00bbd27aa90105e5978a1bfa Author: ModelHub XC Date: Fri Jun 26 19:00:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ddf0c7a --- /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 +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.IQ4_XS.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.IQ4_XS.gguf new file mode 100644 index 0000000..f2937e1 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ed84e79cc371a1039d6e0a6f2acfe783dcb5ee8604785eb3dc28b95c8924a9 +size 5223171936 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q2_K.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q2_K.gguf new file mode 100644 index 0000000..8740883 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f04cac0c8fbdc7ff0befbab899c9841d57a1f70662c133db67815f859cf387 +size 3805398880 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_L.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_L.gguf new file mode 100644 index 0000000..4563590 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a229fc007090f1d78b18499defa06aaf96f73491ee77ee305cff597f54d2455a +size 5132453728 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_M.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_M.gguf new file mode 100644 index 0000000..d793b7b --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5276fa2fa2eb27122fdaf757c4eaab085ba74855895263b3693f3d68a7ea95 +size 4761782112 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_S.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_S.gguf new file mode 100644 index 0000000..09760f9 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12688c05913beaafa713c7835208a40eb2acbf311f94bc843491d381f6d33356 +size 4337665888 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_M.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_M.gguf new file mode 100644 index 0000000..d35cc2e --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9abeaf53cf77a8722823e70317212ac44054419fca5532232a2484b609ef3e +size 5761058656 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_S.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_S.gguf new file mode 100644 index 0000000..82e444d --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcfbec05f431556fc8d3a341d1dd267d0bb8dd01432c1a2cac8ecd17e6ff8d85 +size 5478926176 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_M.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_M.gguf new file mode 100644 index 0000000..d8f1c23 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c4bae454c5e7d388465379806fa84e52f12edacc0ecde6826529480dfbef65 +size 6647367520 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_S.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_S.gguf new file mode 100644 index 0000000..2bee481 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82728a83a8489b03ca3249922f8c4746d72d241c9415a054f61f324668a39386 +size 6483593056 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q6_K.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q6_K.gguf new file mode 100644 index 0000000..3615d70 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5026418d1aa48bfb50aaa924421543b60bc76d5ca420685ec78bd9091bb1e1 +size 7589070688 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q8_0.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q8_0.gguf new file mode 100644 index 0000000..ae91ce1 --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b0065bd64730124d804ce05af434fc55c70cbcb0165ba326996db74c5e7ec2 +size 9827149664 diff --git a/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.f16.gguf b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.f16.gguf new file mode 100644 index 0000000..2871c8b --- /dev/null +++ b/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efb07b758ff9159357ecbdac5aa9de86a383062cb5c1fe0d73f268a0dc7863c +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2158f55 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B + + +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-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B-GGUF/resolve/main/MT4-Gen5-GP-gemma-2-MTMMT3g4-9B.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. + +