commit e869a8e6035b48b6f94d687ca630fff5ac81e77c Author: ModelHub XC Date: Sun Jun 21 19:14:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-reasoningfinetune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9560af6 --- /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-reasoningfinetune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-reasoningfinetune.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..294f863 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Elcaida/gemma-3-reasoningfinetune +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3_text +--- +## About + + + + + + +static quants of https://huggingface.co/Elcaida/gemma-3-reasoningfinetune + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-reasoningfinetune-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-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-reasoningfinetune-GGUF/resolve/main/gemma-3-reasoningfinetune.f16.gguf) | f16 | 2.1 | 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-reasoningfinetune.IQ4_XS.gguf b/gemma-3-reasoningfinetune.IQ4_XS.gguf new file mode 100644 index 0000000..d5e5cb8 --- /dev/null +++ b/gemma-3-reasoningfinetune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eca21e97f3975c6244c20597dcab22141bcb815d089612755b425e377d3c3d99 +size 718168064 diff --git a/gemma-3-reasoningfinetune.Q2_K.gguf b/gemma-3-reasoningfinetune.Q2_K.gguf new file mode 100644 index 0000000..f34fdba --- /dev/null +++ b/gemma-3-reasoningfinetune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b916a67f661da33d3019f3b73a6fcf049ea140a0b4288b25c7ad4d79cbe067a +size 689815040 diff --git a/gemma-3-reasoningfinetune.Q3_K_L.gguf b/gemma-3-reasoningfinetune.Q3_K_L.gguf new file mode 100644 index 0000000..a1d843e --- /dev/null +++ b/gemma-3-reasoningfinetune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593ee423032d0017e6e1366fbd7ad2a9fb593d7ca69e3f4d4901835283709dbd +size 751576064 diff --git a/gemma-3-reasoningfinetune.Q3_K_M.gguf b/gemma-3-reasoningfinetune.Q3_K_M.gguf new file mode 100644 index 0000000..1b733d4 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1afad43cd7872aa021d60827f3bc4c581c37527599ef16134f3ebb05a0bf2ad +size 722416640 diff --git a/gemma-3-reasoningfinetune.Q3_K_S.gguf b/gemma-3-reasoningfinetune.Q3_K_S.gguf new file mode 100644 index 0000000..555b374 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e86ee627bf30cd99b23de13408e28819e3dd99a0e83cfcb35604dff7d8741c +size 688856576 diff --git a/gemma-3-reasoningfinetune.Q4_K_M.gguf b/gemma-3-reasoningfinetune.Q4_K_M.gguf new file mode 100644 index 0000000..b8ab270 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40b16750d41b726a0112e4d59542c3af9763434194a2e26150729cc91610286 +size 806058752 diff --git a/gemma-3-reasoningfinetune.Q4_K_S.gguf b/gemma-3-reasoningfinetune.Q4_K_S.gguf new file mode 100644 index 0000000..4b387c8 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef47837cecc61d4c6e75873256d91882821cca35953f3917131fffc0df927646 +size 780993536 diff --git a/gemma-3-reasoningfinetune.Q5_K_M.gguf b/gemma-3-reasoningfinetune.Q5_K_M.gguf new file mode 100644 index 0000000..12dd930 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1658f842976ac648867d317d35e8652f64df59739f6a4a04f52e67d2c212849b +size 851346176 diff --git a/gemma-3-reasoningfinetune.Q5_K_S.gguf b/gemma-3-reasoningfinetune.Q5_K_S.gguf new file mode 100644 index 0000000..5690158 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0ae0eeb851b4dd9f836f37722e353249553df542c4724e4e5f457ee71a1b8b +size 836400128 diff --git a/gemma-3-reasoningfinetune.Q6_K.gguf b/gemma-3-reasoningfinetune.Q6_K.gguf new file mode 100644 index 0000000..a8cadf6 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315c227b7908611b397bca8d33387d1fc931851a3c186df2ced328df6d5529bb +size 1011739136 diff --git a/gemma-3-reasoningfinetune.Q8_0.gguf b/gemma-3-reasoningfinetune.Q8_0.gguf new file mode 100644 index 0000000..7811bd3 --- /dev/null +++ b/gemma-3-reasoningfinetune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378f3d40eb5e4fce140792427dbf27a3da6a0eb5960b92491f40bdee64667106 +size 1069306880 diff --git a/gemma-3-reasoningfinetune.f16.gguf b/gemma-3-reasoningfinetune.f16.gguf new file mode 100644 index 0000000..6704df7 --- /dev/null +++ b/gemma-3-reasoningfinetune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46f2271cf9cd683ae09f546928df86098fb518e8de2049b9f4b2292204d51c3 +size 2006574080