commit 6823dbb26d6eed4894384be09220386b78926a1b Author: ModelHub XC Date: Mon Jul 20 15:41:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..749e85c --- /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 +GoG-RL-Qwen3-8B-Thinking.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-RL-Qwen3-8B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GoG-RL-Qwen3-8B-Thinking.IQ4_XS.gguf b/GoG-RL-Qwen3-8B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..edc8b34 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f57445834a8b6ec914cf4a61e6228beb9159c25a4e31466b6ab27577370d2d +size 4593297952 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q2_K.gguf b/GoG-RL-Qwen3-8B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..c31c163 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29072ca96f95744f048e40517d1fd1ca22345c15c44fc15f9f1168e01bdf792 +size 3281734176 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q3_K_L.gguf b/GoG-RL-Qwen3-8B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..9a787ad --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf858c3d0e918daeb607f0abbb538b61a963c7b0a74faabffc182d47d04132c +size 4431395360 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q3_K_M.gguf b/GoG-RL-Qwen3-8B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..ef20617 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd2a05a8bc0a5b96af74eb5887b464d3204c760a266747e1d4310c9c62013c5 +size 4124162592 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q3_K_S.gguf b/GoG-RL-Qwen3-8B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..6ea7eec --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89e14fb39cfdac50bfea815135edfd3899e5bd358b52c57b26969375b347f3c +size 3769612832 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q4_K_M.gguf b/GoG-RL-Qwen3-8B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..3e934b3 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b62b42690659c8d9b0872ceb5c1709571eaeb01e893928c47851e0a7e9ae3570 +size 5027785248 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q4_K_S.gguf b/GoG-RL-Qwen3-8B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..a6ce0c7 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86d867a92f8d8c594bd28e77f95bc322a0e504ee1e7d3b91f4264775c2a56c2 +size 4802013728 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q5_K_M.gguf b/GoG-RL-Qwen3-8B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..fcaa92b --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9007c49c51fb94da20644620f2fd3146244b71415b606899e15b1ac61ed94e2b +size 5851114016 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q5_K_S.gguf b/GoG-RL-Qwen3-8B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..10b50d0 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fc146a8203f72eb21de81fd587a7cff0749632f939aae85533dd13b3c81e62 +size 5720762912 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q6_K.gguf b/GoG-RL-Qwen3-8B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..8feea49 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c293fcec4758a541f076505d0ae6eb997565cc85206c7481fbf19795ee2c0fc4 +size 6725900832 diff --git a/GoG-RL-Qwen3-8B-Thinking.Q8_0.gguf b/GoG-RL-Qwen3-8B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..c4bfd8f --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229e84995672aadda86b08905097c28d89663851fc4a99ef1ebb06ee54b1b704 +size 8709519904 diff --git a/GoG-RL-Qwen3-8B-Thinking.f16.gguf b/GoG-RL-Qwen3-8B-Thinking.f16.gguf new file mode 100644 index 0000000..66f9836 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9565f5c7b10f03bd8084075d38fbd7832d720554fe7275fc352fca1d4acc4396 +size 16388045344 diff --git a/GoG-RL-Qwen3-8B-Thinking.mmproj-Q8_0.gguf b/GoG-RL-Qwen3-8B-Thinking.mmproj-Q8_0.gguf new file mode 100644 index 0000000..a39ac4a --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb68b9e1b2460f7436c4476b2236ec166fe11e3300acd2b53da91064120478f +size 752289824 diff --git a/GoG-RL-Qwen3-8B-Thinking.mmproj-f16.gguf b/GoG-RL-Qwen3-8B-Thinking.mmproj-f16.gguf new file mode 100644 index 0000000..9448e71 --- /dev/null +++ b/GoG-RL-Qwen3-8B-Thinking.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5d2cadd635a5b439ff941658989193baacaacc74c575b680a4afee4691ca0c +size 1159029920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c2c584 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Edwinzz/GoG-RL-Qwen3-8B-Thinking +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Edwinzz/GoG-RL-Qwen3-8B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GoG-RL-Qwen3-8B-Thinking-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/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-RL-Qwen3-8B-Thinking-GGUF/resolve/main/GoG-RL-Qwen3-8B-Thinking.f16.gguf) | f16 | 16.5 | 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. + +