commit ee6a9c6116446bac65cb8bcf35637694d55cbdfd Author: ModelHub XC Date: Wed Jun 10 20:04:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..20e5dc9 --- /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 +GPT-Distill-Qwen3-8B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-Distill-Qwen3-8B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT-Distill-Qwen3-8B-Thinking.IQ4_XS.gguf b/GPT-Distill-Qwen3-8B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..448941b --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896200aff26bdbb293761e0114accc9b0c64d376fc4b92cdaa4d5b270b2ecb75 +size 4593296544 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q2_K.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..e8adfe3 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b832543a99f927ae81c43049aacc9d013bcab7b19a620a239d5e6ecd2a6333ef +size 3281732768 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q3_K_L.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..385ad86 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d43a75a637189e9e99a777eda38e07cd5e66a44a24cbdd333ea9ccc510c9cc +size 4431393952 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q3_K_M.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..8276b6b --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4888c72e2cc7dc273aa6aa2c7303508c102c71aec64d6d38030bcf719cfb2206 +size 4124161184 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q3_K_S.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..0c2eb4b --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1582dd00792d1cb5ea3fd1657e4a4808996e1e1bb9c45d8fb35f4e4e882a5a +size 3769611424 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q4_K_M.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..92de886 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f3bd96cc82f7c621f15896c0a14afe2696932ca72013b39a57a127a1a5f588 +size 5027783840 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q4_K_S.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..d4edc8a --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5da08b0f02b0100ecac73db8e3858d5c47c6d425a1289589d868e79c718773 +size 4802012320 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q5_K_M.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..64ae6af --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d5b84096ae1fe6078d2a5d6a99786db65e09f9a1b8a2fe764d4a7bf7b1f239 +size 5851112608 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q5_K_S.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..f873615 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7076ddd77b3343177ad7c24c8c456f240617b082600c00298b5c83875c27af +size 5720761504 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q6_K.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..5a5f25c --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500c18600ba9b31b423b759ae2911ec089fb7bce59733f6c7ade487c790f3207 +size 6725899424 diff --git a/GPT-Distill-Qwen3-8B-Thinking.Q8_0.gguf b/GPT-Distill-Qwen3-8B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..03140e6 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d28ee263288f2dd5ab1c8d25aeebdf28f09192d46c93e9185a72bc0b6c83db +size 8709518496 diff --git a/GPT-Distill-Qwen3-8B-Thinking.f16.gguf b/GPT-Distill-Qwen3-8B-Thinking.f16.gguf new file mode 100644 index 0000000..7a898b9 --- /dev/null +++ b/GPT-Distill-Qwen3-8B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cc669f747eb36d53f8988cebaecb6e43606f40a09557aab73b6a6c36636f49 +size 16388043936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5fbee7a --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Jackrong/GPT-Distill-Qwen3-8B-Thinking +datasets: +- Jackrong/Natural-Reasoning-gpt-oss-120B-S1 +- Jackrong/Chinese-Qwen3-235B-Thinking-2507-Distill-100k +- Jackrong/ShareGPT-gpt-oss-120B-reasoning +- Jackrong/gpt-oss-120b-Reasoning-Instruction +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- sft +- chain-of-thought +- reasoning +- qwen +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/GPT-Distill-Qwen3-8B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT-Distill-Qwen3-8B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-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/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-Qwen3-8B-Thinking.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-Distill-Qwen3-8B-Thinking-GGUF/resolve/main/GPT-Distill-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. + +