commit 374a97f987b11c1f92209943042bcb05832231aa Author: ModelHub XC Date: Mon Jun 15 06:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/saiga_gemma3_12b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c56a069 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +saiga_gemma3_12b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +saiga_gemma3_12b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dae4547 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: IlyaGusev/saiga_gemma3_12b +datasets: +- IlyaGusev/saiga_scored +- IlyaGusev/saiga_preferences +language: +- ru +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/IlyaGusev/saiga_gemma3_12b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#saiga_gemma3_12b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/saiga_gemma3_12b-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/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q3_K_M.gguf) | Q3_K_M | 6.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q3_K_L.gguf) | Q3_K_L | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.IQ4_XS.gguf) | IQ4_XS | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q4_K_S.gguf) | Q4_K_S | 7.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q4_K_M.gguf) | Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q5_K_S.gguf) | Q5_K_S | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q5_K_M.gguf) | Q5_K_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q6_K.gguf) | Q6_K | 9.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/saiga_gemma3_12b-GGUF/resolve/main/saiga_gemma3_12b.Q8_0.gguf) | Q8_0 | 12.6 | fast, best quality | + +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/saiga_gemma3_12b.IQ4_XS.gguf b/saiga_gemma3_12b.IQ4_XS.gguf new file mode 100644 index 0000000..1ae7be2 --- /dev/null +++ b/saiga_gemma3_12b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5e798d4d601d4a18c3d1d7e957b4c981778319daf6872223a86ef8524602c3 +size 6606260480 diff --git a/saiga_gemma3_12b.Q2_K.gguf b/saiga_gemma3_12b.Q2_K.gguf new file mode 100644 index 0000000..498363e --- /dev/null +++ b/saiga_gemma3_12b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59bfbd03e0259852c3fa7ec5136909c553ce826d6407656abae4a2514c1adbe0 +size 4768221440 diff --git a/saiga_gemma3_12b.Q3_K_L.gguf b/saiga_gemma3_12b.Q3_K_L.gguf new file mode 100644 index 0000000..9d7a563 --- /dev/null +++ b/saiga_gemma3_12b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780bcd403f03d77c91f186ad4e03b93434957554f81cabb0fad567f802579182 +size 6480185600 diff --git a/saiga_gemma3_12b.Q3_K_M.gguf b/saiga_gemma3_12b.Q3_K_M.gguf new file mode 100644 index 0000000..ebc9fb0 --- /dev/null +++ b/saiga_gemma3_12b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34756f878c79803d5d5885ca5a0bda5c378a8de798af7279cd721ab9c9b58cf5 +size 6008817920 diff --git a/saiga_gemma3_12b.Q3_K_S.gguf b/saiga_gemma3_12b.Q3_K_S.gguf new file mode 100644 index 0000000..3c9f0be --- /dev/null +++ b/saiga_gemma3_12b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8403eeb37a556d5816995df46a7d0760e3af8c56f0b0550c2f2b94440cc507ac +size 5458315520 diff --git a/saiga_gemma3_12b.Q4_K_M.gguf b/saiga_gemma3_12b.Q4_K_M.gguf new file mode 100644 index 0000000..9fa3f17 --- /dev/null +++ b/saiga_gemma3_12b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a52057a45767c85189ec9118f0e938439862f297404071ae088ce28e05425a +size 7300778240 diff --git a/saiga_gemma3_12b.Q4_K_S.gguf b/saiga_gemma3_12b.Q4_K_S.gguf new file mode 100644 index 0000000..5b8f5c4 --- /dev/null +++ b/saiga_gemma3_12b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2ae31c8796240bfa7012323bb2c908423d3bdf6f2f82ae23cb176a0223b23c +size 6935333120 diff --git a/saiga_gemma3_12b.Q5_K_M.gguf b/saiga_gemma3_12b.Q5_K_M.gguf new file mode 100644 index 0000000..fae75b5 --- /dev/null +++ b/saiga_gemma3_12b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0869d43fd32c22e8a60c50d49697d9fbd7f25207c0e5125a3c4309dec6ceaf +size 8445036800 diff --git a/saiga_gemma3_12b.Q5_K_S.gguf b/saiga_gemma3_12b.Q5_K_S.gguf new file mode 100644 index 0000000..15229c9 --- /dev/null +++ b/saiga_gemma3_12b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f26d4b3da5701340e8dc5ec38e4289e4877dedc776a1cb4aa0cb05ea08b89d4 +size 8231962880 diff --git a/saiga_gemma3_12b.Q6_K.gguf b/saiga_gemma3_12b.Q6_K.gguf new file mode 100644 index 0000000..0e53c48 --- /dev/null +++ b/saiga_gemma3_12b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06e1dea1777f8b2c1e9bac85c2f138d94b3fa5b99f470480c2a403e263a9337 +size 9660811520 diff --git a/saiga_gemma3_12b.Q8_0.gguf b/saiga_gemma3_12b.Q8_0.gguf new file mode 100644 index 0000000..0825f5b --- /dev/null +++ b/saiga_gemma3_12b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8a482046a17add9486c9edfbfa132ce4d5240412dc032f97faf572f2b9464b +size 12510212480 diff --git a/saiga_gemma3_12b.mmproj-Q8_0.gguf b/saiga_gemma3_12b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..761d13d --- /dev/null +++ b/saiga_gemma3_12b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9724e4d2c2835f7b9c250425a8dfc4247c58f7e98f0efb04002ad912c4507f6f +size 594327264 diff --git a/saiga_gemma3_12b.mmproj-f16.gguf b/saiga_gemma3_12b.mmproj-f16.gguf new file mode 100644 index 0000000..47673b2 --- /dev/null +++ b/saiga_gemma3_12b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0790d9c7d309c67b92ece7561c88815c016c4df328934435794a3e4a967e0df +size 854201184