commit b1077264823b8a6eb0d5e0e1d0e062cd5cc586d3 Author: ModelHub XC Date: Sun Jun 14 07:28:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-3-4B-IT-TextOnly-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..562a89b --- /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-3-4B-IT-TextOnly.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-IT-TextOnly.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-3-4B-IT-TextOnly.IQ4_XS.gguf b/Gemma-3-4B-IT-TextOnly.IQ4_XS.gguf new file mode 100644 index 0000000..922000c --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7494feafb48e9838aae0a140834be8f17810d19bebec6c5010839ce8fb5eaaef +size 2279625984 diff --git a/Gemma-3-4B-IT-TextOnly.Q2_K.gguf b/Gemma-3-4B-IT-TextOnly.Q2_K.gguf new file mode 100644 index 0000000..6cc73fe --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934b7597a5f540094578d5ba9490ab71945d2a8d0778693312a828ee392a3d93 +size 1729164544 diff --git a/Gemma-3-4B-IT-TextOnly.Q3_K_L.gguf b/Gemma-3-4B-IT-TextOnly.Q3_K_L.gguf new file mode 100644 index 0000000..43705b0 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0127734e5d49343bdb79cc9ce228a89973a17ae5f7cde6368bbdeaa138ddf4 +size 2236085504 diff --git a/Gemma-3-4B-IT-TextOnly.Q3_K_M.gguf b/Gemma-3-4B-IT-TextOnly.Q3_K_M.gguf new file mode 100644 index 0000000..97cd5f0 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6d0627c5753646dd55dac0e3bdf57e90430b74ffab6de981149f1401060b67 +size 2098459904 diff --git a/Gemma-3-4B-IT-TextOnly.Q3_K_S.gguf b/Gemma-3-4B-IT-TextOnly.Q3_K_S.gguf new file mode 100644 index 0000000..5d656cf --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cef8e53b67114f5c5986d7216b57a614a1f25159074a7d442a381b5809f6952 +size 1937364224 diff --git a/Gemma-3-4B-IT-TextOnly.Q4_K_M.gguf b/Gemma-3-4B-IT-TextOnly.Q4_K_M.gguf new file mode 100644 index 0000000..7a8deba --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056ad78535130be3ffbb46f2083048b23d76f9a1495fc2a730503fdf2ccc9bb4 +size 2489894144 diff --git a/Gemma-3-4B-IT-TextOnly.Q4_K_S.gguf b/Gemma-3-4B-IT-TextOnly.Q4_K_S.gguf new file mode 100644 index 0000000..cdf8770 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01338ae2f8da9664fece472c0f3d135cedae5d56d33f947a024b5bb640e254ad +size 2377929984 diff --git a/Gemma-3-4B-IT-TextOnly.Q5_K_M.gguf b/Gemma-3-4B-IT-TextOnly.Q5_K_M.gguf new file mode 100644 index 0000000..69d99e9 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0760030d7d0327abdaeed8d1234111876940b745c24176bf3da35b400a55fa5e +size 2829698304 diff --git a/Gemma-3-4B-IT-TextOnly.Q5_K_S.gguf b/Gemma-3-4B-IT-TextOnly.Q5_K_S.gguf new file mode 100644 index 0000000..c4e4023 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94fe3765843af0007938cd749ef8c279b344ad6176894c55bc6302a5995c5782 +size 2764592384 diff --git a/Gemma-3-4B-IT-TextOnly.Q6_K.gguf b/Gemma-3-4B-IT-TextOnly.Q6_K.gguf new file mode 100644 index 0000000..350d640 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1238e13fdaa6a525be710b737096244bc9f1ff9d9b0a3d27170486be7c44816 +size 3190740224 diff --git a/Gemma-3-4B-IT-TextOnly.Q8_0.gguf b/Gemma-3-4B-IT-TextOnly.Q8_0.gguf new file mode 100644 index 0000000..1059d9f --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6c95f401b5eea6984c031f92c3c169c4dc0d541866687257ce648033c5dd8b +size 4130402304 diff --git a/Gemma-3-4B-IT-TextOnly.f16.gguf b/Gemma-3-4B-IT-TextOnly.f16.gguf new file mode 100644 index 0000000..24d7f93 --- /dev/null +++ b/Gemma-3-4B-IT-TextOnly.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1699dd2c32a7a5c3090984768f76cf372f1b4eeba53b3738fc4052cca23aa8b6 +size 7767803904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b83eab8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Leoxxxxh/Gemma-3-4B-IT-TextOnly +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Leoxxxxh/Gemma-3-4B-IT-TextOnly + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-3-4B-IT-TextOnly-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-IT-TextOnly-GGUF/resolve/main/Gemma-3-4B-IT-TextOnly.f16.gguf) | f16 | 7.9 | 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. + +