commit 658a95b63bf5a2ea33dad8c4ca7076f50e0070bb Author: ModelHub XC Date: Fri Jun 12 02:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d89224 --- /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 +gemma-3-4b-it-Ko-Reasoning.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it-Ko-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a96f25 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: DimensionSTP/gemma-3-4b-it-Ko-Reasoning +language: +- ko +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- korean +- reasoning +- instruction-tuning +- fine-tuning +- gemma3 +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DimensionSTP/gemma-3-4b-it-Ko-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-4b-it-Ko-Reasoning-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-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-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-it-Ko-Reasoning-GGUF/resolve/main/gemma-3-4b-it-Ko-Reasoning.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/gemma-3-4b-it-Ko-Reasoning.IQ4_XS.gguf b/gemma-3-4b-it-Ko-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..039e7a2 --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7014fc3bb42402d058d575cd5f5711bfe0bc9b895b122ca3692bb04dd395d0ca +size 2279496512 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q2_K.gguf b/gemma-3-4b-it-Ko-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..25ff48d --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905e4cecb8f2d10a1d12dac48fbe46fc14f40f34af63fd03dd4ef5dffd6e2b5c +size 1729035072 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q3_K_L.gguf b/gemma-3-4b-it-Ko-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..306f46c --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69896f6ef92408f9f4752959f82fae5639a3ef1cee5354e4361dbe3b4b9c48d +size 2235956032 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q3_K_M.gguf b/gemma-3-4b-it-Ko-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..96500a3 --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01395193e7515a48c039045a434d0f11fef507ad3a57f4a5a1e4005f5f43ff29 +size 2098330432 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q3_K_S.gguf b/gemma-3-4b-it-Ko-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..09c40f4 --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4592e61da8d61687e53654aae76735b20d8f31964cc92adce48ea435c3023b3e +size 1937234752 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q4_K_M.gguf b/gemma-3-4b-it-Ko-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..be87c6d --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2db01fd4bf104ceac8ea334bd3bb4f566e5e581c06f92d61a0c6d6d360481c9 +size 2489764672 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q4_K_S.gguf b/gemma-3-4b-it-Ko-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..f3dcb11 --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69dc575d88d11c0b56f0aef9b9fa8ec48385a6c0321d5efe34340358a652943f +size 2377800512 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q5_K_M.gguf b/gemma-3-4b-it-Ko-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..5d40647 --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d28901910326d2a1e41fd869c96c3b0db89a3cc80f429afb8d74882c7b0e0d4 +size 2829568832 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q5_K_S.gguf b/gemma-3-4b-it-Ko-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..d0e5a1c --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfddc2d774318a5c6b249809125d86404ce8546ed2bd02f43a85f24d233917f +size 2764462912 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q6_K.gguf b/gemma-3-4b-it-Ko-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..f56503f --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e0d14141bd042b4f00a132d179e7127bb202edd6a6a03188e3158e6382145c +size 3190610752 diff --git a/gemma-3-4b-it-Ko-Reasoning.Q8_0.gguf b/gemma-3-4b-it-Ko-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..6b83e0c --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87f5453e609313b75bcce63e8665aeb189fdb7cdbae04464ccf3b6ac0530a764 +size 4130235008 diff --git a/gemma-3-4b-it-Ko-Reasoning.f16.gguf b/gemma-3-4b-it-Ko-Reasoning.f16.gguf new file mode 100644 index 0000000..839a57f --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48858c4c08f4f155c62a0817ad8be0d32e896c240cd08f9d57656de42dd25577 +size 7767490208 diff --git a/gemma-3-4b-it-Ko-Reasoning.mmproj-Q8_0.gguf b/gemma-3-4b-it-Ko-Reasoning.mmproj-Q8_0.gguf new file mode 100644 index 0000000..be7bebc --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d84c9635d01d5d30dfdaeeb76ee4032951f8157c25da2e635f9977360e4406 +size 591377664 diff --git a/gemma-3-4b-it-Ko-Reasoning.mmproj-f16.gguf b/gemma-3-4b-it-Ko-Reasoning.mmproj-f16.gguf new file mode 100644 index 0000000..771f21e --- /dev/null +++ b/gemma-3-4b-it-Ko-Reasoning.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e6534af96e415def4991406e9413eae558956fd32f85f49f600d7d2384e27f +size 851251584