commit 3ae2f847e520d4b9bd1e289accc3c3da43289dd3 Author: ModelHub XC Date: Mon Jun 15 12:08:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..05e0fcf --- /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-oss-120b-Distill-Qwen3-4B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-120b-Distill-Qwen3-4B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5677457 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Jackrong/gpt-oss-120b-Distill-Qwen3-4B-Thinking +datasets: +- Jackrong/Natural-Reasoning-gpt-oss-120B-S1 +- Jackrong/ShareGPT-gpt-oss-120B-reasoning +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/gpt-oss-120b-Distill-Qwen3-4B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-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-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-120b-Distill-Qwen3-4B-Thinking-GGUF/resolve/main/gpt-oss-120b-Distill-Qwen3-4B-Thinking.f16.gguf) | f16 | 8.2 | 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/gpt-oss-120b-Distill-Qwen3-4B-Thinking.IQ4_XS.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..54647db --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c78426bb1c48aad3dad99d783401d59feefe20231c4126fb4798bce087b4fab +size 2286315520 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q2_K.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..8e6bdf3 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ff5c629784bc745122e554b41795bf18ae4f2fbe9269cbc36933a9233c4a9f +size 1669498880 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_L.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..fbe6b6d --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54bcb5cb304482e3d18cbf8671f7189c01c1a7f40879574fe395f9ba4d0a424 +size 2239784960 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_M.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..33fd5d9 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd332ccb1f275feaf62aac1ad7e804f7dc17a51cb9a9633309a7b367dd1b80e +size 2075617280 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_S.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..8881664 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6100406c1c88fb23fc0efb745433b8df82b5e10e78acc09420d113ab3ae2bcd +size 1886996480 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_M.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..d91891d --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1baff41d6de11abeca2c284a8c24cbc07a341a04d00da38addc57cdc08cae494 +size 2497280000 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_S.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..5cc089f --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d2d1a1d65612aee0804da63bc420703b3a4cc2b0dfac1a0fe545c5af69993c +size 2383308800 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_M.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..a5769af --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9d8ace66aa760c8f482a156a66ff52ac11f9f1b306a8166559ae863d4ae775 +size 2889512960 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_S.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..4483a43 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25bae604baa08aa632f2e05a4da082ddc3e4902b1f565136acf12532c1617c3d +size 2823710720 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q6_K.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..25e6d68 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74de676246f6f1cf1df6e8557236dbe88b5ee8603500f28eb0559765eef70b6b +size 3306260480 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q8_0.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..87a0a0c --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc4e8c4bdb30483321f66c0141063d741156c451c9fc799b1e56f8d300a4556 +size 4280404480 diff --git a/gpt-oss-120b-Distill-Qwen3-4B-Thinking.f16.gguf b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.f16.gguf new file mode 100644 index 0000000..9407f54 --- /dev/null +++ b/gpt-oss-120b-Distill-Qwen3-4B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c7a24ee80b8325143e6108f679f917c5a099929ab8ed0708f8ecd96b286d6f +size 8051284480