commit 1ee22dbec57477150c26823691a5801de9ee9451 Author: ModelHub XC Date: Sun Jun 14 16:12:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2-9b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c960387 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +gemma-2-9b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ab2240 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: google/gemma-2-9b-it +extra_gated_button_content: Acknowledge license +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/google/gemma-2-9b-it + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-2-9b-it-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/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.IQ3_XS.gguf) | IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.IQ3_S.gguf) | IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.IQ3_M.gguf) | IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-GGUF/resolve/main/gemma-2-9b-it.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. + + diff --git a/gemma-2-9b-it.IQ3_M.gguf b/gemma-2-9b-it.IQ3_M.gguf new file mode 100644 index 0000000..c3db2d1 --- /dev/null +++ b/gemma-2-9b-it.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394ed120c32d2c07ba4879b46bb485fe0907520a2e21a8003713133df6f6e971 +size 4494616640 diff --git a/gemma-2-9b-it.IQ3_S.gguf b/gemma-2-9b-it.IQ3_S.gguf new file mode 100644 index 0000000..7ed8c61 --- /dev/null +++ b/gemma-2-9b-it.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2456ba800746f1cf3ccfaca4b61be57e2394a8f9baba172854ba580e8211e905 +size 4337666112 diff --git a/gemma-2-9b-it.IQ3_XS.gguf b/gemma-2-9b-it.IQ3_XS.gguf new file mode 100644 index 0000000..759df08 --- /dev/null +++ b/gemma-2-9b-it.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a13f15500acd2515f9babd6d59adbb40e636cb81fc8c127d1edc17803f46fd +size 4144990272 diff --git a/gemma-2-9b-it.IQ4_XS.gguf b/gemma-2-9b-it.IQ4_XS.gguf new file mode 100644 index 0000000..1de37d8 --- /dev/null +++ b/gemma-2-9b-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3175251e00b27f350e24ce1961d3d829c5d51a946e89162a0b54ea7c5a5c94 +size 5223172160 diff --git a/gemma-2-9b-it.Q2_K.gguf b/gemma-2-9b-it.Q2_K.gguf new file mode 100644 index 0000000..74154ee --- /dev/null +++ b/gemma-2-9b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfd8126401722824b77d8a2f80936d490ee77698d9083ce841932085bb8d040 +size 3805399104 diff --git a/gemma-2-9b-it.Q3_K_L.gguf b/gemma-2-9b-it.Q3_K_L.gguf new file mode 100644 index 0000000..3c22c06 --- /dev/null +++ b/gemma-2-9b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa88ebc6e2db1738f48b51b7111dc942fe30ba6aaca3fbdbfced995cb1861035 +size 5132453952 diff --git a/gemma-2-9b-it.Q3_K_M.gguf b/gemma-2-9b-it.Q3_K_M.gguf new file mode 100644 index 0000000..0497891 --- /dev/null +++ b/gemma-2-9b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca35094512e5e6aa55b700924bed5e0a6355a99857241e592cb4e279bf5169e1 +size 4761782336 diff --git a/gemma-2-9b-it.Q3_K_S.gguf b/gemma-2-9b-it.Q3_K_S.gguf new file mode 100644 index 0000000..4b746cc --- /dev/null +++ b/gemma-2-9b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629a63382bc967d6868717ea35d489b19af3306f4684e2f9172294c56a73e4d3 +size 4337666112 diff --git a/gemma-2-9b-it.Q4_K_M.gguf b/gemma-2-9b-it.Q4_K_M.gguf new file mode 100644 index 0000000..e4f694c --- /dev/null +++ b/gemma-2-9b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da1d1ada7f64adea359bc4a572cb6faa6e4fc26993f621a3fec7ed614ca337e +size 5761058880 diff --git a/gemma-2-9b-it.Q4_K_S.gguf b/gemma-2-9b-it.Q4_K_S.gguf new file mode 100644 index 0000000..a7d8ccb --- /dev/null +++ b/gemma-2-9b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62330173ccfe6d9e10c2b129d0c12855c1a214106b8a8b525ccc897c942ca09 +size 5478926400 diff --git a/gemma-2-9b-it.Q5_K_M.gguf b/gemma-2-9b-it.Q5_K_M.gguf new file mode 100644 index 0000000..12ac672 --- /dev/null +++ b/gemma-2-9b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c353c3d2400f95d6d8a3ef30d25038ef1b04a52964ed33438a1926c854fac4e8 +size 6647367744 diff --git a/gemma-2-9b-it.Q5_K_S.gguf b/gemma-2-9b-it.Q5_K_S.gguf new file mode 100644 index 0000000..d3e51f4 --- /dev/null +++ b/gemma-2-9b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9362b1a89e08af57d1e698e5035c2e708f50155791a34bcbfe71c19fc4711cd8 +size 6483593280 diff --git a/gemma-2-9b-it.Q6_K.gguf b/gemma-2-9b-it.Q6_K.gguf new file mode 100644 index 0000000..62e1b57 --- /dev/null +++ b/gemma-2-9b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1b9ed754b63a0798eb6dcf2a5c76c39c4ba99c47fb34901b9c30217b7ef0ff +size 7589070912 diff --git a/gemma-2-9b-it.Q8_0.gguf b/gemma-2-9b-it.Q8_0.gguf new file mode 100644 index 0000000..2d90e58 --- /dev/null +++ b/gemma-2-9b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bea65d24a267e86b3a9a706d920f53d667fbd6531e97099649cfae2e4219ad +size 9827149888 diff --git a/gemma-2-9b-it.f16.gguf b/gemma-2-9b-it.f16.gguf new file mode 100644 index 0000000..99a917e --- /dev/null +++ b/gemma-2-9b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5cffe22cd10610540e93e36e43a95543a7069848cfdbda0cc5189e863f75fd +size 18490681408