commit 60d84459358f1da6410e0939f6d7855a09bea9a3 Author: ModelHub XC Date: Sun Jun 14 07:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma3-Rhino-27B-RAG-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8eb6705 --- /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 +Gemma3-Rhino-27B-RAG.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-Rhino-27B-RAG.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma3-Rhino-27B-RAG.IQ4_XS.gguf b/Gemma3-Rhino-27B-RAG.IQ4_XS.gguf new file mode 100644 index 0000000..8bf0fdc --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9630e6e68286bfd84ec118bb75b998b7025d0723daab0d044559ca1ad2263053 +size 2279626432 diff --git a/Gemma3-Rhino-27B-RAG.Q2_K.gguf b/Gemma3-Rhino-27B-RAG.Q2_K.gguf new file mode 100644 index 0000000..0c302ae --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378c2ccdd31b6217cb4d6a1ddcda12ec61894c2974740275bdea50edc5b0faeb +size 1729164992 diff --git a/Gemma3-Rhino-27B-RAG.Q3_K_L.gguf b/Gemma3-Rhino-27B-RAG.Q3_K_L.gguf new file mode 100644 index 0000000..d530618 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:719ce6191fcb6fc6b9e013bacb6cc709e254fdd3be235bd4e0ada00728c5e63f +size 2236085952 diff --git a/Gemma3-Rhino-27B-RAG.Q3_K_M.gguf b/Gemma3-Rhino-27B-RAG.Q3_K_M.gguf new file mode 100644 index 0000000..3950528 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9363d07d1940d05b6aa5a96c2fe37b188fa2aad4115fbc58b2796773ba64b9 +size 2098460352 diff --git a/Gemma3-Rhino-27B-RAG.Q3_K_S.gguf b/Gemma3-Rhino-27B-RAG.Q3_K_S.gguf new file mode 100644 index 0000000..d2946d2 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e526b32ffa469f5bf3a99aef32c34987cd3e39aea4b9ec4c93b17bb9bc1795 +size 1937364672 diff --git a/Gemma3-Rhino-27B-RAG.Q4_K_M.gguf b/Gemma3-Rhino-27B-RAG.Q4_K_M.gguf new file mode 100644 index 0000000..547b918 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0589ec182df128d570518a1d94d9a63d7f48bf390b197d35ffab58f6d74721d4 +size 2489894592 diff --git a/Gemma3-Rhino-27B-RAG.Q4_K_S.gguf b/Gemma3-Rhino-27B-RAG.Q4_K_S.gguf new file mode 100644 index 0000000..9dac1c7 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0443e9772ea4224e320b66568da47cb4e2607fd91242cafebd7e7a5f63931adc +size 2377930432 diff --git a/Gemma3-Rhino-27B-RAG.Q5_K_M.gguf b/Gemma3-Rhino-27B-RAG.Q5_K_M.gguf new file mode 100644 index 0000000..9e1de6a --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6be1a3edc7fcce33a008352e59e85950a307216f3e3969933cb6cda94c200e +size 2829698752 diff --git a/Gemma3-Rhino-27B-RAG.Q5_K_S.gguf b/Gemma3-Rhino-27B-RAG.Q5_K_S.gguf new file mode 100644 index 0000000..97f9f94 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8841b5fbd2dadba32282ca3623fe073e33ceda19860d8a3c92f2aa2ba63a3eda +size 2764592832 diff --git a/Gemma3-Rhino-27B-RAG.Q6_K.gguf b/Gemma3-Rhino-27B-RAG.Q6_K.gguf new file mode 100644 index 0000000..f5ec9ac --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298d4c79f6ca73095990fe691cf924b16196aa4bcf9009bd8323868e236af837 +size 3190740672 diff --git a/Gemma3-Rhino-27B-RAG.Q8_0.gguf b/Gemma3-Rhino-27B-RAG.Q8_0.gguf new file mode 100644 index 0000000..a4bd382 --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb5df98c36693bb9e702cdc7006a92ca850e93fb426ff4df0e3d6b360a5e453 +size 4130402752 diff --git a/Gemma3-Rhino-27B-RAG.f16.gguf b/Gemma3-Rhino-27B-RAG.f16.gguf new file mode 100644 index 0000000..a9a668b --- /dev/null +++ b/Gemma3-Rhino-27B-RAG.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e017fc1a57b3c14234efb8b4623282f0dbe90653249a7d32bf0878bc6a809def +size 7767804352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93577c1 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: QomSSLab/Gemma3-Rhino-27B-RAG +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3 +--- +## About + + + + + + +static quants of https://huggingface.co/QomSSLab/Gemma3-Rhino-27B-RAG + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma3-Rhino-27B-RAG-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/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-Rhino-27B-RAG-GGUF/resolve/main/Gemma3-Rhino-27B-RAG.f16.gguf) | f16 | 7.9 | 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. + +