commit 640bde3d3cd02f6be8f864aaf4fef6a66027a31b Author: ModelHub XC Date: Tue Jun 16 20:38:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma3-4B-CoT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f89252 --- /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-CoT.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma3-4B-CoT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma3-4B-CoT.IQ4_XS.gguf b/Gemma3-4B-CoT.IQ4_XS.gguf new file mode 100644 index 0000000..2a81c7f --- /dev/null +++ b/Gemma3-4B-CoT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380df66730a76f7981f3e62d3f688e513f878e5ff1573fe87932fe2bc0ce58f7 +size 2279495168 diff --git a/Gemma3-4B-CoT.Q2_K.gguf b/Gemma3-4B-CoT.Q2_K.gguf new file mode 100644 index 0000000..c48bdfd --- /dev/null +++ b/Gemma3-4B-CoT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9d237289545617ebea7d4174eb2aa9593e25ba4be0ec03bddf1f0af64ac4e7 +size 1729033728 diff --git a/Gemma3-4B-CoT.Q3_K_L.gguf b/Gemma3-4B-CoT.Q3_K_L.gguf new file mode 100644 index 0000000..cefd5bd --- /dev/null +++ b/Gemma3-4B-CoT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c51c5afc73e44b9e5e5f8090e6242234dd09d5c63660576c68e25453195090 +size 2235954688 diff --git a/Gemma3-4B-CoT.Q3_K_M.gguf b/Gemma3-4B-CoT.Q3_K_M.gguf new file mode 100644 index 0000000..25b4323 --- /dev/null +++ b/Gemma3-4B-CoT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73024c888388c00c427749f9a59cfb38180a2370b87568ebafd9ca1e846b6d44 +size 2098329088 diff --git a/Gemma3-4B-CoT.Q3_K_S.gguf b/Gemma3-4B-CoT.Q3_K_S.gguf new file mode 100644 index 0000000..e6698f5 --- /dev/null +++ b/Gemma3-4B-CoT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8bb64250cc3b39c241354dc1b24eb420e7f7155c3a1058106909aa2674ddf15 +size 1937233408 diff --git a/Gemma3-4B-CoT.Q4_K_M.gguf b/Gemma3-4B-CoT.Q4_K_M.gguf new file mode 100644 index 0000000..72c6094 --- /dev/null +++ b/Gemma3-4B-CoT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d5273279b7781815d0c255e2136f02113317ce35ba73216ada5b28271f08e0 +size 2489763328 diff --git a/Gemma3-4B-CoT.Q4_K_S.gguf b/Gemma3-4B-CoT.Q4_K_S.gguf new file mode 100644 index 0000000..ef07882 --- /dev/null +++ b/Gemma3-4B-CoT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe902ef21a66513063d51b0fc8eae965efc73e3450d6143f27d2098882b369d +size 2377799168 diff --git a/Gemma3-4B-CoT.Q5_K_M.gguf b/Gemma3-4B-CoT.Q5_K_M.gguf new file mode 100644 index 0000000..ffb09fa --- /dev/null +++ b/Gemma3-4B-CoT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f72490687db6a868734aad3c4e213562459c4ecaaa9d03982fec117cee6deb0 +size 2829567488 diff --git a/Gemma3-4B-CoT.Q5_K_S.gguf b/Gemma3-4B-CoT.Q5_K_S.gguf new file mode 100644 index 0000000..0b354d7 --- /dev/null +++ b/Gemma3-4B-CoT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0485c3c1c58df0991380845ea32f6be854cfda93f24fefe9560674535e337d9 +size 2764461568 diff --git a/Gemma3-4B-CoT.Q6_K.gguf b/Gemma3-4B-CoT.Q6_K.gguf new file mode 100644 index 0000000..09d391e --- /dev/null +++ b/Gemma3-4B-CoT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e95e796681092fed856b70b0b64b1cc8140614feaeec1f5422b2db22a67dc2 +size 3190609408 diff --git a/Gemma3-4B-CoT.Q8_0.gguf b/Gemma3-4B-CoT.Q8_0.gguf new file mode 100644 index 0000000..f156bdd --- /dev/null +++ b/Gemma3-4B-CoT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e23a1778f05fb3f6783124e3b00f6a3aaf127f271e75498ac7b3814134806f +size 4130233664 diff --git a/Gemma3-4B-CoT.f16.gguf b/Gemma3-4B-CoT.f16.gguf new file mode 100644 index 0000000..2911efe --- /dev/null +++ b/Gemma3-4B-CoT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04a0adb6557ab1872b56f551f4ef13565ae5cfc0c312d57c0de46f5aeb22a2c +size 7767488864 diff --git a/Gemma3-4B-CoT.mmproj-Q8_0.gguf b/Gemma3-4B-CoT.mmproj-Q8_0.gguf new file mode 100644 index 0000000..2e0c7b3 --- /dev/null +++ b/Gemma3-4B-CoT.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2337f8f59c6ea6f3ae3837363013a1e897a17d9ab4bacbd189f30ad9b391f9da +size 591377920 diff --git a/Gemma3-4B-CoT.mmproj-f16.gguf b/Gemma3-4B-CoT.mmproj-f16.gguf new file mode 100644 index 0000000..ce4b9fa --- /dev/null +++ b/Gemma3-4B-CoT.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ea58125fc2c47c26fb710bced7abc0533bc7bb608444badef02c2c85747ee1 +size 851251840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad40614 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: DrRiceIO7/Gemma3-4B-CoT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DrRiceIO7/Gemma3-4B-CoT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma3-4B-CoT-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-CoT-GGUF/resolve/main/Gemma3-4B-CoT.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CoT-GGUF/resolve/main/Gemma3-4B-CoT.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. + +