commit 6b11df5dc5fd8106721870ebde1bdc133a36f2b8 Author: ModelHub XC Date: Fri Apr 24 14:49:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1691170 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..70ab455 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: tomaszki/gemma-3 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +no_imatrix: '[125]14.4143,nan detected in blk.1.attn_q.weight' +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/tomaszki/gemma-3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-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-3-GGUF/resolve/main/gemma-3.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-GGUF/resolve/main/gemma-3.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-3.IQ4_XS.gguf b/gemma-3.IQ4_XS.gguf new file mode 100644 index 0000000..7bb40e7 --- /dev/null +++ b/gemma-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cda4ab9a423505b6e15bf9d0c528da80617d92e4297de1a15597b3cd1368ce0 +size 1501219232 diff --git a/gemma-3.Q2_K.gguf b/gemma-3.Q2_K.gguf new file mode 100644 index 0000000..45d91ec --- /dev/null +++ b/gemma-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:730d5a71a1d6c11642c94ce4acfa6f8c4ae3156901e7d4447b0c30659917db0e +size 1157925280 diff --git a/gemma-3.Q3_K_L.gguf b/gemma-3.Q3_K_L.gguf new file mode 100644 index 0000000..fa590ac --- /dev/null +++ b/gemma-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff67de5a30a80e28452f95330fd3060b5869046e3cc41f95bb4043a6e76b2717 +size 1465592224 diff --git a/gemma-3.Q3_K_M.gguf b/gemma-3.Q3_K_M.gguf new file mode 100644 index 0000000..db1fbaf --- /dev/null +++ b/gemma-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23690b1d59fa94805b7c470ff4ed539bfa322a73375f7bb215d3728244e45138 +size 1383803296 diff --git a/gemma-3.Q3_K_S.gguf b/gemma-3.Q3_K_S.gguf new file mode 100644 index 0000000..1f27184 --- /dev/null +++ b/gemma-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42ff4fd5f7b312f19eaf1839747221c025eb0a6e40670de09a61d5e8f1320d6 +size 1287981472 diff --git a/gemma-3.Q4_K_M.gguf b/gemma-3.Q4_K_M.gguf new file mode 100644 index 0000000..a417d54 --- /dev/null +++ b/gemma-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d8bba6461dc050038c5de252856d18fa355e5377eb19c3045d2f214ff12628 +size 1630263712 diff --git a/gemma-3.Q4_K_S.gguf b/gemma-3.Q4_K_S.gguf new file mode 100644 index 0000000..43d682f --- /dev/null +++ b/gemma-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21909c081c595c0cde589878edb07e278a2096044df84c481ddc77266987828 +size 1559841184 diff --git a/gemma-3.Q5_K_M.gguf b/gemma-3.Q5_K_M.gguf new file mode 100644 index 0000000..e227be9 --- /dev/null +++ b/gemma-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510dd9158e31c2fe7ce3df9cd49673d8d142bd300e8234c9055c8c25a1204a24 +size 1839651232 diff --git a/gemma-3.Q5_K_S.gguf b/gemma-3.Q5_K_S.gguf new file mode 100644 index 0000000..c8dbe1f --- /dev/null +++ b/gemma-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977a04b5b7044b2ad8bd052029ea1ce316ab9f687d46f02a0ab36ea3e5391bd5 +size 1798916512 diff --git a/gemma-3.Q6_K.gguf b/gemma-3.Q6_K.gguf new file mode 100644 index 0000000..6c3dc85 --- /dev/null +++ b/gemma-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9206f648dadde41f7ec91cc0f0ad0976a43cf07add9d28dd84a859ebe76977e +size 2062125472 diff --git a/gemma-3.Q8_0.gguf b/gemma-3.Q8_0.gguf new file mode 100644 index 0000000..28d27a3 --- /dev/null +++ b/gemma-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d376975138a846119bd7b1247cdd84160eb5558e9d8a584c6893f5e47cd5d7c5 +size 2669070752 diff --git a/gemma-3.f16.gguf b/gemma-3.f16.gguf new file mode 100644 index 0000000..55b1b5d --- /dev/null +++ b/gemma-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82b435a24ffd088bf5539d90ec137f745f0f2e68cd08b3f3a4e9ad3bc37bac6 +size 5018536352