commit a7e1b7b5ae8c025416e99e6e7fcfab0e0f96e2a4 Author: ModelHub XC Date: Sun Jun 14 16:16:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2-9b-it-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43bc0c6 --- /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-it.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-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..5e555eb --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +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 + + + + + + +weighted/imatrix quants of https://huggingface.co/google/gemma-2-9b-it + + +static quants are available at https://huggingface.co/mradermacher/gemma-2-9b-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-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-i1-GGUF/resolve/main/gemma-2-9b-it.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-it.i1-IQ1_M.gguf b/gemma-2-9b-it.i1-IQ1_M.gguf new file mode 100644 index 0000000..9c3ce6d --- /dev/null +++ b/gemma-2-9b-it.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472b1285b0367bae88850bca2bed092f6a07549bee2c4b2f63f65323c2edf0cc +size 2545953056 diff --git a/gemma-2-9b-it.i1-IQ1_S.gguf b/gemma-2-9b-it.i1-IQ1_S.gguf new file mode 100644 index 0000000..01c1829 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e148951a783e1665d88b8add30fa1c53b673c6239f82e98bfbf5c4dc82a7b8df +size 2378565920 diff --git a/gemma-2-9b-it.i1-IQ2_M.gguf b/gemma-2-9b-it.i1-IQ2_M.gguf new file mode 100644 index 0000000..9f9fa96 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155d6ba5404f4b05f298583d4c2dd0acdd2c82726c848dd93d3a88e85ace8743 +size 3434670368 diff --git a/gemma-2-9b-it.i1-IQ2_S.gguf b/gemma-2-9b-it.i1-IQ2_S.gguf new file mode 100644 index 0000000..870aca8 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466d801d5b71663af7aa54d348bc87ade36dbe0d5e57ea1de50312ee51e0fe49 +size 3211487520 diff --git a/gemma-2-9b-it.i1-IQ2_XS.gguf b/gemma-2-9b-it.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b606a46 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba956cca32a342a6a35e394ad647a71a6f11cf24eb43970d5456987eda7eae6 +size 3067382048 diff --git a/gemma-2-9b-it.i1-IQ2_XXS.gguf b/gemma-2-9b-it.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ae2254a --- /dev/null +++ b/gemma-2-9b-it.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ceae8022dff318f6a226cf2f0dd1ffe76e4fa1b5e66210aa55ca8590ff59fea +size 2824931616 diff --git a/gemma-2-9b-it.i1-IQ3_M.gguf b/gemma-2-9b-it.i1-IQ3_M.gguf new file mode 100644 index 0000000..4e723fa --- /dev/null +++ b/gemma-2-9b-it.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015adaf66a7b0aaf649f417b8ac3a85160bb61fcb1122958d9ad35a212ca40e0 +size 4494616864 diff --git a/gemma-2-9b-it.i1-IQ3_S.gguf b/gemma-2-9b-it.i1-IQ3_S.gguf new file mode 100644 index 0000000..bfa1de4 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715683fba6bbfe08289cdaf7df8f9df4767a95bbbaf03ae3171b254d1129d16a +size 4337666336 diff --git a/gemma-2-9b-it.i1-IQ3_XS.gguf b/gemma-2-9b-it.i1-IQ3_XS.gguf new file mode 100644 index 0000000..10b3b39 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331ff555e8944a8c1cd489f64730cd8faf94cd9cc610a91b80322062cbea350b +size 4144990496 diff --git a/gemma-2-9b-it.i1-IQ3_XXS.gguf b/gemma-2-9b-it.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4d631d5 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7898fd12a3610d0fad59e26e721b2ed38b4ddc9a6871445449e7e5875a6aeb37 +size 3796740384 diff --git a/gemma-2-9b-it.i1-IQ4_XS.gguf b/gemma-2-9b-it.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3a61e58 --- /dev/null +++ b/gemma-2-9b-it.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43402f46dff03b9db2f283f52a38d986c4acd30bc9b50dd21a06f5692c0cec11 +size 5183031584 diff --git a/gemma-2-9b-it.i1-Q2_K.gguf b/gemma-2-9b-it.i1-Q2_K.gguf new file mode 100644 index 0000000..e13a294 --- /dev/null +++ b/gemma-2-9b-it.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f93897cda3f57a86e4b67825af8d856b77ed0fc6178c69370d6356b51e040a +size 3805399328 diff --git a/gemma-2-9b-it.i1-Q3_K_L.gguf b/gemma-2-9b-it.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0837005 --- /dev/null +++ b/gemma-2-9b-it.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4309b4cbafa6245a12fbba6a0cc925ccdc8472a6c1007e6ad4e77329479616 +size 5132454176 diff --git a/gemma-2-9b-it.i1-Q3_K_M.gguf b/gemma-2-9b-it.i1-Q3_K_M.gguf new file mode 100644 index 0000000..95d7530 --- /dev/null +++ b/gemma-2-9b-it.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02dbe889b7e2122734116074bfc3ebce9290d75f10d9c47c28e1edc30e9ee31 +size 4761782560 diff --git a/gemma-2-9b-it.i1-Q3_K_S.gguf b/gemma-2-9b-it.i1-Q3_K_S.gguf new file mode 100644 index 0000000..df172d0 --- /dev/null +++ b/gemma-2-9b-it.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b1f957a633ac3c9eb2139fd0f344cba66217c5b67a72d0fd508df38035613c +size 4337666336 diff --git a/gemma-2-9b-it.i1-Q4_0.gguf b/gemma-2-9b-it.i1-Q4_0.gguf new file mode 100644 index 0000000..eb3c330 --- /dev/null +++ b/gemma-2-9b-it.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2300f461ca3b7344cc2652374da251fca95941a8490f534d7126ed1f572289e +size 5459200288 diff --git a/gemma-2-9b-it.i1-Q4_K_M.gguf b/gemma-2-9b-it.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8dd3b44 --- /dev/null +++ b/gemma-2-9b-it.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdbb7695db264a3fe45066437509c1f6ce86acae348a317aed40a8922d7a604 +size 5761059104 diff --git a/gemma-2-9b-it.i1-Q4_K_S.gguf b/gemma-2-9b-it.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9ddbe0b --- /dev/null +++ b/gemma-2-9b-it.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5034d149c73a0f9728d57926136b08529bdea7232faedcf69f576c13c73c7ef +size 5478926624 diff --git a/gemma-2-9b-it.i1-Q5_K_M.gguf b/gemma-2-9b-it.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3e7308a --- /dev/null +++ b/gemma-2-9b-it.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19998b2f45caa26cc429f8394012c03b18c2a7c61ba9741b1c00cc3607839d17 +size 6647367968 diff --git a/gemma-2-9b-it.i1-Q5_K_S.gguf b/gemma-2-9b-it.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2a69fe3 --- /dev/null +++ b/gemma-2-9b-it.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0133a0c6af164ed5dceaad87aa697509bac5eece8529bc072f2efc62e6c1bb91 +size 6483593504 diff --git a/gemma-2-9b-it.i1-Q6_K.gguf b/gemma-2-9b-it.i1-Q6_K.gguf new file mode 100644 index 0000000..85d8134 --- /dev/null +++ b/gemma-2-9b-it.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4b1493b27c0d7a683ae030b3a3e9e83599cd96ef866b3d0205b938de44659a +size 7589071136 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..c89a4e5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7949e076395611b02b76ebe68b3e60b6a69283ceb0d83ffdf0f4e426423d3d72 +size 6116891