commit 1d16272fbf4242439dff36232776906a753525f5 Author: ModelHub XC Date: Sun Jun 14 14:15:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-1.1-2b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..23061ad --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-1.1-2b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-1.1-2b-it.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..159c87d --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: google/gemma-1.1-2b-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 + + + + + + +static quants of https://huggingface.co/google/gemma-1.1-2b-it + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-1.1-2b-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-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-1.1-2b-it-GGUF/resolve/main/gemma-1.1-2b-it.f16.gguf) | f16 | 5.1 | 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-1.1-2b-it.IQ4_XS.gguf b/gemma-1.1-2b-it.IQ4_XS.gguf new file mode 100644 index 0000000..870b6e6 --- /dev/null +++ b/gemma-1.1-2b-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a9c118ec556cb8ac658833b66e26dcae6f4ba6cfbf93b7f15d6cab7e1a1e14 +size 1501219296 diff --git a/gemma-1.1-2b-it.Q2_K.gguf b/gemma-1.1-2b-it.Q2_K.gguf new file mode 100644 index 0000000..6d88b4f --- /dev/null +++ b/gemma-1.1-2b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebda43b201cd80785ac4d54963ec92835a1507571af81d5d3357d6545351f0a +size 1157925344 diff --git a/gemma-1.1-2b-it.Q3_K_L.gguf b/gemma-1.1-2b-it.Q3_K_L.gguf new file mode 100644 index 0000000..273d3cf --- /dev/null +++ b/gemma-1.1-2b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e6f4f1e3fa5234ded9cf84f9cda4da61f70aeca03ced9ba3eff3d69b1d0c927 +size 1465592288 diff --git a/gemma-1.1-2b-it.Q3_K_M.gguf b/gemma-1.1-2b-it.Q3_K_M.gguf new file mode 100644 index 0000000..033ad52 --- /dev/null +++ b/gemma-1.1-2b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a2404512b70c06377fb2067c010ae2e3f67bc9c512ad738f61449eeab12a97 +size 1383803360 diff --git a/gemma-1.1-2b-it.Q3_K_S.gguf b/gemma-1.1-2b-it.Q3_K_S.gguf new file mode 100644 index 0000000..158b3ed --- /dev/null +++ b/gemma-1.1-2b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561cf5cdf3456a260b1ad803f296b8006097a5d3db49e74a9e2ce756cc882884 +size 1287981536 diff --git a/gemma-1.1-2b-it.Q4_0_4_4.gguf b/gemma-1.1-2b-it.Q4_0_4_4.gguf new file mode 100644 index 0000000..4bea781 --- /dev/null +++ b/gemma-1.1-2b-it.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8440c9f658e30542b6d1ca2a07a2db7f6fa7ddba413fc6260253d2769cbb62d8 +size 1551190496 diff --git a/gemma-1.1-2b-it.Q4_K_M.gguf b/gemma-1.1-2b-it.Q4_K_M.gguf new file mode 100644 index 0000000..6effb57 --- /dev/null +++ b/gemma-1.1-2b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880a68e18d4213e2819853c3a5a3638c5ab19a86291753a0fb92106f672ee707 +size 1630263776 diff --git a/gemma-1.1-2b-it.Q4_K_S.gguf b/gemma-1.1-2b-it.Q4_K_S.gguf new file mode 100644 index 0000000..5397786 --- /dev/null +++ b/gemma-1.1-2b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75442a407b49d3e997dc29dc291e67d3e4e64a10879239d96d2517048041f94b +size 1559841248 diff --git a/gemma-1.1-2b-it.Q5_K_M.gguf b/gemma-1.1-2b-it.Q5_K_M.gguf new file mode 100644 index 0000000..34b0dc9 --- /dev/null +++ b/gemma-1.1-2b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8191f32b15d85c8aeb37c6ec627a620a6eff2e5e510dcc2d5f84ac57572af9 +size 1839651296 diff --git a/gemma-1.1-2b-it.Q5_K_S.gguf b/gemma-1.1-2b-it.Q5_K_S.gguf new file mode 100644 index 0000000..1212b02 --- /dev/null +++ b/gemma-1.1-2b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1acc552fdf13fa1e86a33b8cf16355368175d38540c446a00196e011f007053f +size 1798916576 diff --git a/gemma-1.1-2b-it.Q6_K.gguf b/gemma-1.1-2b-it.Q6_K.gguf new file mode 100644 index 0000000..46be321 --- /dev/null +++ b/gemma-1.1-2b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c44edd40ffe859a830cc565521fd947a4914fdff56764691133ddd21cf9188 +size 2062125536 diff --git a/gemma-1.1-2b-it.Q8_0.gguf b/gemma-1.1-2b-it.Q8_0.gguf new file mode 100644 index 0000000..ea873e3 --- /dev/null +++ b/gemma-1.1-2b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d19bcb851cc58da70e217f3b398089296fa994a963447ac4b9840c0bc9e715 +size 2669070816 diff --git a/gemma-1.1-2b-it.f16.gguf b/gemma-1.1-2b-it.f16.gguf new file mode 100644 index 0000000..d965977 --- /dev/null +++ b/gemma-1.1-2b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f3c1e124baf2d87a6e089b6b38e513be13556bdf2f3ca90c95dc7ecc2c66db +size 5018536416