commit f6c94ca86d06827b6f64a9a0af70eb42b2c2ca1c Author: ModelHub XC Date: Mon Jun 15 10:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b82da1a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma3_4b_mulitmodal_sft_02-02-2026.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ddee8e5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: SF-Foundation/gemma3_4b_mulitmodal_sft_02-02-2026 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SF-Foundation/gemma3_4b_mulitmodal_sft_02-02-2026 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma3_4b_mulitmodal_sft_02-02-2026-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/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma3_4b_mulitmodal_sft_02-02-2026-GGUF/resolve/main/gemma3_4b_mulitmodal_sft_02-02-2026.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. + + diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.IQ4_XS.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.IQ4_XS.gguf new file mode 100644 index 0000000..f0d744c --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4013db7d0541cff9c0ef4fa28107ce6b0a446e6326eaaf7c7fd0099126de41 +size 2279626176 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q2_K.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q2_K.gguf new file mode 100644 index 0000000..42c27d0 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4fe8f1fd045799e7a3c3f56e0be5b1cfc05cbd42d270a0ae500e00dcaf2783d +size 1729164736 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_L.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_L.gguf new file mode 100644 index 0000000..b1b3a9f --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db672e1bff0b3b30e717d86d92af57a77352f82c8fb6c57347fe4094715f1ed +size 2236085696 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_M.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_M.gguf new file mode 100644 index 0000000..5cc1394 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d6eb947e008c5ebe4008f28a1bfe98d8794252c191c4d3bf919b428d31da8d7 +size 2098460096 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_S.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_S.gguf new file mode 100644 index 0000000..94bb1be --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb10dd007fd25b5ab48982aae3e61c750b2b8ae772858b03045b7048458c7b0 +size 1937364416 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_M.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_M.gguf new file mode 100644 index 0000000..8144cdd --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c959805b8d9334c3e71800cfc32a869582566681f75ebbdf191e40e430a1b64 +size 2489894336 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_S.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_S.gguf new file mode 100644 index 0000000..50ec155 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a02b290033b484dbe73dc9842f1189ba33b4030260ec10a700fbb4ea0207a2 +size 2377930176 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_M.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_M.gguf new file mode 100644 index 0000000..1e7b2e0 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f30f7d731aa0938bd0d1ef5803506a17c2871a8f90643f51e677d43e5402fd +size 2829698496 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_S.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_S.gguf new file mode 100644 index 0000000..b682385 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2d258d79299eeff2050aa5f88176fc2d0a43b997f1ce5e185d014a42d687f1 +size 2764592576 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q6_K.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q6_K.gguf new file mode 100644 index 0000000..efb40b4 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a2792d7389c468ff549fc5b1442ef955534514fd1014bab0f39fae27b9d7ad +size 3190740416 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.Q8_0.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.Q8_0.gguf new file mode 100644 index 0000000..d46732c --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6391369186a529914bd82224d939723846098f5916957c62ea2a4810d93024 +size 4130402496 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.f16.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.f16.gguf new file mode 100644 index 0000000..0a40858 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6debc92e1374d120fdcb2b9e7e5421f5652ea14f110ba9a396da2a63a5e0f38e +size 7767804096 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-Q8_0.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-Q8_0.gguf new file mode 100644 index 0000000..3ec2696 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2063e4bf022a9d47a30e4e922da7e15ef865ebfb48fad9898b8d0d7a5cadad2d +size 591377504 diff --git a/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-f16.gguf b/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-f16.gguf new file mode 100644 index 0000000..e4c5b01 --- /dev/null +++ b/gemma3_4b_mulitmodal_sft_02-02-2026.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c601bf4eb1c94c81283a3958c9640b764e60db374e5d6d95389879a820a42b7f +size 851251424