commit 3d84cafe1f5ed6ebef399dd934a9c8d00ca98b80 Author: ModelHub XC Date: Sun Jun 14 14:40:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2-27b-it-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7918478 --- /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-2-27b-it.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it.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..742df62 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: google/gemma-2-27b-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 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/google/gemma-2-27b-it + + +static quants are available at https://huggingface.co/mradermacher/gemma-2-27b-it-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-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-i1-GGUF/resolve/main/gemma-2-27b-it.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | 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-2-27b-it.i1-IQ1_M.gguf b/gemma-2-27b-it.i1-IQ1_M.gguf new file mode 100644 index 0000000..45c08cd --- /dev/null +++ b/gemma-2-27b-it.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af128decc9c7f0b6967091ec410216760913d429bbe88e09031a44ef086fc31e +size 6692471680 diff --git a/gemma-2-27b-it.i1-IQ1_S.gguf b/gemma-2-27b-it.i1-IQ1_S.gguf new file mode 100644 index 0000000..0443b95 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e8a73c742789e550b30f0f1da42b04e92fcf4c2046f8388ed594aea1d96582 +size 6132433792 diff --git a/gemma-2-27b-it.i1-IQ2_M.gguf b/gemma-2-27b-it.i1-IQ2_M.gguf new file mode 100644 index 0000000..8d8adde --- /dev/null +++ b/gemma-2-27b-it.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17fbabb5c504c4b66dd3e305039856204b126893374ec9549ec416175a551bd +size 9398879104 diff --git a/gemma-2-27b-it.i1-IQ2_S.gguf b/gemma-2-27b-it.i1-IQ2_S.gguf new file mode 100644 index 0000000..44b9634 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5725e264de34048160cb58940e0ef0baf0b776367b4187cef9e90b4c4aa922 +size 8652161920 diff --git a/gemma-2-27b-it.i1-IQ2_XS.gguf b/gemma-2-27b-it.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7de0942 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd425d74422f81af44884f658f467dec0349b1c80a02990b150fe6c891140d4d +size 8399717248 diff --git a/gemma-2-27b-it.i1-IQ2_XXS.gguf b/gemma-2-27b-it.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..85f5bdf --- /dev/null +++ b/gemma-2-27b-it.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f198b079202f07634e5a9c69e597433429623d12d6af34e3119a0d852d17e515 +size 7625868160 diff --git a/gemma-2-27b-it.i1-IQ3_M.gguf b/gemma-2-27b-it.i1-IQ3_M.gguf new file mode 100644 index 0000000..e79c829 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d983c6a07f87ed5b3b20fd296aea177cbaefd35bd4c7e8ac1c463b8abc319d5e +size 12454830976 diff --git a/gemma-2-27b-it.i1-IQ3_S.gguf b/gemma-2-27b-it.i1-IQ3_S.gguf new file mode 100644 index 0000000..52ada99 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539f1900cdd5ad5e51386d5d6f2b71404bbc62d6007cffafd249bc35729c35e3 +size 12169061248 diff --git a/gemma-2-27b-it.i1-IQ3_XS.gguf b/gemma-2-27b-it.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8d5dd59 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c570df23babcddcfa757ac066ca2c53c7422eedba2f1e3d2a46f8ad148b100f0 +size 11550630784 diff --git a/gemma-2-27b-it.i1-IQ3_XXS.gguf b/gemma-2-27b-it.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cdc9c0d --- /dev/null +++ b/gemma-2-27b-it.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2154989fd826fbbdf52800663d6859c34d3419d5493c62963d06fb1745f1bc8d +size 10750755712 diff --git a/gemma-2-27b-it.i1-IQ4_XS.gguf b/gemma-2-27b-it.i1-IQ4_XS.gguf new file mode 100644 index 0000000..38e6950 --- /dev/null +++ b/gemma-2-27b-it.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db9006073d3e862dcc8df03a9e7edf785469003d01c74073210efd7c3ebca2c +size 14814421888 diff --git a/gemma-2-27b-it.i1-Q2_K.gguf b/gemma-2-27b-it.i1-Q2_K.gguf new file mode 100644 index 0000000..0adc8fc --- /dev/null +++ b/gemma-2-27b-it.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf6452a7a71429b721ced39ef795311a20dcf80eece4ac38a343378e2ed53da +size 10449576832 diff --git a/gemma-2-27b-it.i1-Q3_K_L.gguf b/gemma-2-27b-it.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d458f28 --- /dev/null +++ b/gemma-2-27b-it.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70c377cfd1bf2d336a10072e89810cf9bf275751e7fffcbf86012c48ab2bb35 +size 14519362432 diff --git a/gemma-2-27b-it.i1-Q3_K_M.gguf b/gemma-2-27b-it.i1-Q3_K_M.gguf new file mode 100644 index 0000000..42df343 --- /dev/null +++ b/gemma-2-27b-it.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa907d161d47687ab844d2c34bd51842f0a6daf0cbb3019179bd4c237fd4c75c +size 13424649088 diff --git a/gemma-2-27b-it.i1-Q3_K_S.gguf b/gemma-2-27b-it.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a39bada --- /dev/null +++ b/gemma-2-27b-it.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a99e12724e9c98c2d3c512c86d677786c5054ca355decfb505f26276f768ec +size 12169061248 diff --git a/gemma-2-27b-it.i1-Q4_0.gguf b/gemma-2-27b-it.i1-Q4_0.gguf new file mode 100644 index 0000000..683359a --- /dev/null +++ b/gemma-2-27b-it.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c5d9893eb9392e8ef053c56149f242d91e7543f4579ad9b4a95f14909561ca +size 15681463168 diff --git a/gemma-2-27b-it.i1-Q4_K_M.gguf b/gemma-2-27b-it.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4c97c92 --- /dev/null +++ b/gemma-2-27b-it.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c5f429472100d03a4bd0d5bf1868fc84c27bfdfec799b3a9ae1959a4517142 +size 16645383040 diff --git a/gemma-2-27b-it.i1-Q4_K_S.gguf b/gemma-2-27b-it.i1-Q4_K_S.gguf new file mode 100644 index 0000000..160812e --- /dev/null +++ b/gemma-2-27b-it.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2888d1c66b35feddc829e2be19df071fc9a3ce3e60c9938a29ac4017448b1129 +size 15739265920 diff --git a/gemma-2-27b-it.i1-Q5_K_M.gguf b/gemma-2-27b-it.i1-Q5_K_M.gguf new file mode 100644 index 0000000..65f236e --- /dev/null +++ b/gemma-2-27b-it.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dafcbd95774929c225814d5416943d9cf00ace8c58da5bad5c1315d46b19980 +size 19408118656 diff --git a/gemma-2-27b-it.i1-Q5_K_S.gguf b/gemma-2-27b-it.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ffe2a22 --- /dev/null +++ b/gemma-2-27b-it.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bb6c225ebe832ae7f801dddf2f42ba3ecad7239ac9b6d87cd5256b2f1fdb9f +size 18884207488 diff --git a/gemma-2-27b-it.i1-Q6_K.gguf b/gemma-2-27b-it.i1-Q6_K.gguf new file mode 100644 index 0000000..6c1cc81 --- /dev/null +++ b/gemma-2-27b-it.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fea99999c56ce95465b6279b2be6ad350b92264fd366893bba626128687ec07 +size 22343525248 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..c5b627d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208ccdee2a61a7021ea04b36128d3ce4e5587db61f1d326ba395882b7d02a937 +size 11786687