commit 9841d148731d3f54dd44eab19dc8962250d27f1c Author: ModelHub XC Date: Sun Jun 14 05:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/helpful_reasoning_qwen3_4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41b3f83 --- /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 +helpful_reasoning_qwen3_4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +helpful_reasoning_qwen3_4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..64e19c9 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: convoicon/helpful_reasoning_qwen3_4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/convoicon/helpful_reasoning_qwen3_4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#helpful_reasoning_qwen3_4B-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/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/helpful_reasoning_qwen3_4B-GGUF/resolve/main/helpful_reasoning_qwen3_4B.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/helpful_reasoning_qwen3_4B.IQ4_XS.gguf b/helpful_reasoning_qwen3_4B.IQ4_XS.gguf new file mode 100644 index 0000000..7c5790a --- /dev/null +++ b/helpful_reasoning_qwen3_4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5a7c77f41fc5b2ca4aec9dfeb6e9e449b3da1edbe9165ec309e4f100f87cad +size 2286316224 diff --git a/helpful_reasoning_qwen3_4B.Q2_K.gguf b/helpful_reasoning_qwen3_4B.Q2_K.gguf new file mode 100644 index 0000000..9cd0d8c --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b334a72ed003adc78404b109cd208d15f2a52910fe40f3a38926e61e957fc60c +size 1669499584 diff --git a/helpful_reasoning_qwen3_4B.Q3_K_L.gguf b/helpful_reasoning_qwen3_4B.Q3_K_L.gguf new file mode 100644 index 0000000..52b62de --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbb047e8fbdec87f20ca7c078553cd8385116e791eaf0cf5b0e0bc7d39583fe +size 2239785664 diff --git a/helpful_reasoning_qwen3_4B.Q3_K_M.gguf b/helpful_reasoning_qwen3_4B.Q3_K_M.gguf new file mode 100644 index 0000000..01ffb7a --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83540c516e750652160e806f8a755bd5091c3291e71ceed95f499c9b7bea62b9 +size 2075617984 diff --git a/helpful_reasoning_qwen3_4B.Q3_K_S.gguf b/helpful_reasoning_qwen3_4B.Q3_K_S.gguf new file mode 100644 index 0000000..309c7ab --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a90cd4e51129919b2711016257c643477ed5288f4bcdabe74487ec9d3759b5ba +size 1886997184 diff --git a/helpful_reasoning_qwen3_4B.Q4_K_M.gguf b/helpful_reasoning_qwen3_4B.Q4_K_M.gguf new file mode 100644 index 0000000..7e75e3b --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a4be33c46a0b0e89de2c215448d45aa381ccba95fc7354b953f1cb2b4b7a17 +size 2497280704 diff --git a/helpful_reasoning_qwen3_4B.Q4_K_S.gguf b/helpful_reasoning_qwen3_4B.Q4_K_S.gguf new file mode 100644 index 0000000..4e399e4 --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6e8a0caf8aaf9afdfde4c2120d7f5e8da458cc808def9b87df371362e535ad +size 2383309504 diff --git a/helpful_reasoning_qwen3_4B.Q5_K_M.gguf b/helpful_reasoning_qwen3_4B.Q5_K_M.gguf new file mode 100644 index 0000000..f953c21 --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66339d518a20d56f921f53ae96689831124d5df6f5738762ee5b56cc4c007d94 +size 2889513664 diff --git a/helpful_reasoning_qwen3_4B.Q5_K_S.gguf b/helpful_reasoning_qwen3_4B.Q5_K_S.gguf new file mode 100644 index 0000000..2d52e16 --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349b3c64d7a99a442aa380171c8ae3acc59d16850f4bb2855544f79b03535852 +size 2823711424 diff --git a/helpful_reasoning_qwen3_4B.Q6_K.gguf b/helpful_reasoning_qwen3_4B.Q6_K.gguf new file mode 100644 index 0000000..3cedc28 --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7255608e0ac0ba1460d7a81a3a96981f682ac09c846893fed81fea9648d8455 +size 3306261184 diff --git a/helpful_reasoning_qwen3_4B.Q8_0.gguf b/helpful_reasoning_qwen3_4B.Q8_0.gguf new file mode 100644 index 0000000..268e0a0 --- /dev/null +++ b/helpful_reasoning_qwen3_4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7d1918fb775d10c94b75aa652aa02b634781972fabe69dad3c1fc8b04a3376 +size 4280405184 diff --git a/helpful_reasoning_qwen3_4B.f16.gguf b/helpful_reasoning_qwen3_4B.f16.gguf new file mode 100644 index 0000000..d3c560c --- /dev/null +++ b/helpful_reasoning_qwen3_4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f8964d5f31ad91a18c0639c6d69d4820422ae71952ab5dd088ae4c5e3de775 +size 8051285184