commit fb8f726e6623e61a789c717803358ad34f4065a4 Author: ModelHub XC Date: Sun Jun 14 16:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2-9b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2a0931 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b61024 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: google/gemma-2-9b +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 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/google/gemma-2-9b + + +static quants are available at https://huggingface.co/mradermacher/gemma-2-9b-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-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-i1-GGUF/resolve/main/gemma-2-9b.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K | + +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. + + diff --git a/gemma-2-9b.i1-IQ1_M.gguf b/gemma-2-9b.i1-IQ1_M.gguf new file mode 100644 index 0000000..d4f22ca --- /dev/null +++ b/gemma-2-9b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753c9bfce90b44b8ceb615ec9ff87d666c35f14be554fd9ab05250b32b44bac0 +size 2545952416 diff --git a/gemma-2-9b.i1-IQ1_S.gguf b/gemma-2-9b.i1-IQ1_S.gguf new file mode 100644 index 0000000..01a59dd --- /dev/null +++ b/gemma-2-9b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ad75ac821f7378c6ec7c02cf7c1aa5d7deb4009d4f2b22863e20be964a296f +size 2378565280 diff --git a/gemma-2-9b.i1-IQ2_M.gguf b/gemma-2-9b.i1-IQ2_M.gguf new file mode 100644 index 0000000..5b8795a --- /dev/null +++ b/gemma-2-9b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ab11c337234b48f50c2185d4c8b26a6c85582b7f6870fc713bdf754dd8b112 +size 3434669728 diff --git a/gemma-2-9b.i1-IQ2_S.gguf b/gemma-2-9b.i1-IQ2_S.gguf new file mode 100644 index 0000000..647c1bf --- /dev/null +++ b/gemma-2-9b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8ccbfe10413053d95c5fe63e4f51de86b338d5452965a6e4225dcb51a6f081 +size 3211486880 diff --git a/gemma-2-9b.i1-IQ2_XS.gguf b/gemma-2-9b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..27d72f7 --- /dev/null +++ b/gemma-2-9b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f49d3c509ebff0e1f5f9afc6a3eb772b49b3450144f0456ae783114c9cca2a +size 3067381408 diff --git a/gemma-2-9b.i1-IQ2_XXS.gguf b/gemma-2-9b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c5e0990 --- /dev/null +++ b/gemma-2-9b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6efb36fcfb20c1100f90aa66b70577b3f85f0cb8a6107c8d3acf1c243f7b18 +size 2824930976 diff --git a/gemma-2-9b.i1-IQ3_M.gguf b/gemma-2-9b.i1-IQ3_M.gguf new file mode 100644 index 0000000..3aaa4c2 --- /dev/null +++ b/gemma-2-9b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadb9197b208bbdb82ca291bf5523b6e95e28b9651cbfe5437f0c4c9b4c45be9 +size 4494616224 diff --git a/gemma-2-9b.i1-IQ3_S.gguf b/gemma-2-9b.i1-IQ3_S.gguf new file mode 100644 index 0000000..4190052 --- /dev/null +++ b/gemma-2-9b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e9481404b25db3cdede147db6c248236af9748276a267ae177fca24f4bfdc1 +size 4337665696 diff --git a/gemma-2-9b.i1-IQ3_XS.gguf b/gemma-2-9b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..443c93a --- /dev/null +++ b/gemma-2-9b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5218d4f87bcd41e3838d9a3842c0b0653423e9672e1ef163427965cffb2a4bbf +size 4144989856 diff --git a/gemma-2-9b.i1-IQ3_XXS.gguf b/gemma-2-9b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8ea89d4 --- /dev/null +++ b/gemma-2-9b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da581d383471cc780c90c665d4d3cbebceeae3191ec34a1de6e2c626e98240e +size 3796739744 diff --git a/gemma-2-9b.i1-IQ4_XS.gguf b/gemma-2-9b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..10bcde1 --- /dev/null +++ b/gemma-2-9b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa329825cde623ba44ad33a3b75c1b19302cc4702d2f82e275f75c8e1569e66a +size 5183030944 diff --git a/gemma-2-9b.i1-Q2_K.gguf b/gemma-2-9b.i1-Q2_K.gguf new file mode 100644 index 0000000..317950b --- /dev/null +++ b/gemma-2-9b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b625e0923e370ba1968b92a63641849e41331966273524aa9213b2e5c44e35b +size 3805398688 diff --git a/gemma-2-9b.i1-Q3_K_L.gguf b/gemma-2-9b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b465245 --- /dev/null +++ b/gemma-2-9b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619227061fdfceac486a1c810d1cce4c4c19bc207e867e6a948f48e263125aea +size 5132453536 diff --git a/gemma-2-9b.i1-Q3_K_M.gguf b/gemma-2-9b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f5309c1 --- /dev/null +++ b/gemma-2-9b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed02120d78c9e085c220e88360d5215fb823f5164235d6b35645dd5adf47b7ba +size 4761781920 diff --git a/gemma-2-9b.i1-Q3_K_S.gguf b/gemma-2-9b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4595c56 --- /dev/null +++ b/gemma-2-9b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e7c7271da5ef8a58b0074f493e2d1d1be170ad8e8716bb736f5814b451bb71 +size 4337665696 diff --git a/gemma-2-9b.i1-Q4_0.gguf b/gemma-2-9b.i1-Q4_0.gguf new file mode 100644 index 0000000..bf40d49 --- /dev/null +++ b/gemma-2-9b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48c643b9c85eb20223ca05589cf865bb5bd5bd10fd58d93feb10d7bee65f846 +size 5459199648 diff --git a/gemma-2-9b.i1-Q4_K_M.gguf b/gemma-2-9b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..84d77e3 --- /dev/null +++ b/gemma-2-9b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a97eca19822f431b473c4efa92b3a87ffd382cde471fc09cf5c169fb28a728 +size 5761058464 diff --git a/gemma-2-9b.i1-Q4_K_S.gguf b/gemma-2-9b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cb05d4e --- /dev/null +++ b/gemma-2-9b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e64b1d70aa8829e562cda05bd6e13cbbb8408f530af4f9f6247d5fb9d8bfc3 +size 5478925984 diff --git a/gemma-2-9b.i1-Q5_K_M.gguf b/gemma-2-9b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8d3c8eb --- /dev/null +++ b/gemma-2-9b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2b1a9d42dce96b1a09b4d52f181a0f5f686cbf95e167ef8b00458b4d43d3f6 +size 6647367328 diff --git a/gemma-2-9b.i1-Q5_K_S.gguf b/gemma-2-9b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..cf9bddd --- /dev/null +++ b/gemma-2-9b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6240aaa5b1fc54b241cb5477364bfa99132aac64dd2c61204fece2cc0eb50a24 +size 6483592864 diff --git a/gemma-2-9b.i1-Q6_K.gguf b/gemma-2-9b.i1-Q6_K.gguf new file mode 100644 index 0000000..80e937c --- /dev/null +++ b/gemma-2-9b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8445d1114afbcb8242d5d1a5dacd76a90d43867c317f63a3b999bd3de2fed58 +size 7589070496 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..17e6ea4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766c13f778ba5d85c2ece2e2c7bc1fa33273e73a3b095b60381532694991074b +size 6116891