commit aeca9a17cbc3f2dbdad3f2567db3fc72e417d603 Author: ModelHub XC Date: Mon Jun 15 01:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwenReasoner-0.5-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b24ab49 --- /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 +QwenReasoner-0.5-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenReasoner-0.5-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwenReasoner-0.5-3B.IQ4_XS.gguf b/QwenReasoner-0.5-3B.IQ4_XS.gguf new file mode 100644 index 0000000..9369673 --- /dev/null +++ b/QwenReasoner-0.5-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46977e6ff84de7757f13ac05bec42d4a98c0e414baedf9d3ab73ef52f6bc40c +size 1753185152 diff --git a/QwenReasoner-0.5-3B.Q2_K.gguf b/QwenReasoner-0.5-3B.Q2_K.gguf new file mode 100644 index 0000000..c555db4 --- /dev/null +++ b/QwenReasoner-0.5-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b1c411b2d082faa57120c8c543da89cddfd83fd141ea5ed6186aecb6859f40 +size 1274755968 diff --git a/QwenReasoner-0.5-3B.Q3_K_L.gguf b/QwenReasoner-0.5-3B.Q3_K_L.gguf new file mode 100644 index 0000000..a2b3fd1 --- /dev/null +++ b/QwenReasoner-0.5-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4b06eaa71cdbce6f739914da9e992ab9159f1fe18ad5fcf2b8e062f77e197c +size 1707391872 diff --git a/QwenReasoner-0.5-3B.Q3_K_M.gguf b/QwenReasoner-0.5-3B.Q3_K_M.gguf new file mode 100644 index 0000000..c3bf303 --- /dev/null +++ b/QwenReasoner-0.5-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836361c8d2b65cb36382817362cf5a48b55f452dc6d5df8131b3bfa390f513ba +size 1590475648 diff --git a/QwenReasoner-0.5-3B.Q3_K_S.gguf b/QwenReasoner-0.5-3B.Q3_K_S.gguf new file mode 100644 index 0000000..1b12a6e --- /dev/null +++ b/QwenReasoner-0.5-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faadf28292d7082d243ae2fb87f89e14c7007cdc922b489bc9540bfc11625b74 +size 1454357376 diff --git a/QwenReasoner-0.5-3B.Q4_K_M.gguf b/QwenReasoner-0.5-3B.Q4_K_M.gguf new file mode 100644 index 0000000..96a205b --- /dev/null +++ b/QwenReasoner-0.5-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063aa335eb7916ccc3efde8639d69b4bb77a3c79ae5233509a41caef7aee826d +size 1929902976 diff --git a/QwenReasoner-0.5-3B.Q4_K_S.gguf b/QwenReasoner-0.5-3B.Q4_K_S.gguf new file mode 100644 index 0000000..7d8f5df --- /dev/null +++ b/QwenReasoner-0.5-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39752ed4ce3df53ec8c4f33fcf69b6e33ce75761ed7bc5edabd19839a75001fe +size 1834384256 diff --git a/QwenReasoner-0.5-3B.Q5_K_M.gguf b/QwenReasoner-0.5-3B.Q5_K_M.gguf new file mode 100644 index 0000000..512edcb --- /dev/null +++ b/QwenReasoner-0.5-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b980fed659ac388196c696876d680fbf94696de0b19885f4b6ba5761e0987022 +size 2224814976 diff --git a/QwenReasoner-0.5-3B.Q5_K_S.gguf b/QwenReasoner-0.5-3B.Q5_K_S.gguf new file mode 100644 index 0000000..375541b --- /dev/null +++ b/QwenReasoner-0.5-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4865a2250e1120fbf5d4da532c55a9e7aa012af620bfdef3602261cc467056a5 +size 2169666432 diff --git a/QwenReasoner-0.5-3B.Q6_K.gguf b/QwenReasoner-0.5-3B.Q6_K.gguf new file mode 100644 index 0000000..de3abe8 --- /dev/null +++ b/QwenReasoner-0.5-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169e96924d94b6ba033ca450b07250b2d3115c4bbc9eba5ddbfa500cc96dfde4 +size 2538158976 diff --git a/QwenReasoner-0.5-3B.Q8_0.gguf b/QwenReasoner-0.5-3B.Q8_0.gguf new file mode 100644 index 0000000..3eab8a3 --- /dev/null +++ b/QwenReasoner-0.5-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada9bbe38e71e443f5cf0660e9f859d576ef43d5b98149167afeff1c5cdfb946 +size 3285476224 diff --git a/QwenReasoner-0.5-3B.f16.gguf b/QwenReasoner-0.5-3B.f16.gguf new file mode 100644 index 0000000..0a13796 --- /dev/null +++ b/QwenReasoner-0.5-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2a4734500ccf74542b44909a7affbce65af59b65b8bdb83aa9cd6551f9deeb +size 6178317184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a528f90 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: oscar128372/QwenReasoner-0.5-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/oscar128372/QwenReasoner-0.5-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QwenReasoner-0.5-3B-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/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReasoner-0.5-3B-GGUF/resolve/main/QwenReasoner-0.5-3B.f16.gguf) | f16 | 6.3 | 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. + +