commit 01513dd6f0b417ef421f06c028a5d97bb3316246 Author: ModelHub XC Date: Thu Jun 4 03:18:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Usefulness-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2522c7a --- /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 +Qwen3-4B-Usefulness.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Usefulness.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Usefulness.IQ4_XS.gguf b/Qwen3-4B-Usefulness.IQ4_XS.gguf new file mode 100644 index 0000000..dd779bb --- /dev/null +++ b/Qwen3-4B-Usefulness.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c41cff02d3bfffedaad72524a3736a37879e8f01519c6f60472f68af29ad7e +size 2286314816 diff --git a/Qwen3-4B-Usefulness.Q2_K.gguf b/Qwen3-4B-Usefulness.Q2_K.gguf new file mode 100644 index 0000000..5fa18a7 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265271bd8359746699deb8702991db3b137b8f19a933d408757532bb2285a8ed +size 1669498176 diff --git a/Qwen3-4B-Usefulness.Q3_K_L.gguf b/Qwen3-4B-Usefulness.Q3_K_L.gguf new file mode 100644 index 0000000..35aff18 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443cda545de1c24203484f65912bf8f90f37d80582f1e6a6738cfdc6be1ed78d +size 2239784256 diff --git a/Qwen3-4B-Usefulness.Q3_K_M.gguf b/Qwen3-4B-Usefulness.Q3_K_M.gguf new file mode 100644 index 0000000..d9e9a9c --- /dev/null +++ b/Qwen3-4B-Usefulness.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d44763bd2ecafa57a9f0629d1d93bff8f0288c535daba9fbb5ad0233e76fd4f +size 2075616576 diff --git a/Qwen3-4B-Usefulness.Q3_K_S.gguf b/Qwen3-4B-Usefulness.Q3_K_S.gguf new file mode 100644 index 0000000..a9fa735 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5983427f40de2a1c0268e12cdc649233b312aee298d1bdb076271defb26a6703 +size 1886995776 diff --git a/Qwen3-4B-Usefulness.Q4_K_M.gguf b/Qwen3-4B-Usefulness.Q4_K_M.gguf new file mode 100644 index 0000000..c550f87 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaecd81986108d37776bd6f3921305c234234ecbb7324231f35a605dc8430ef4 +size 2497279296 diff --git a/Qwen3-4B-Usefulness.Q4_K_S.gguf b/Qwen3-4B-Usefulness.Q4_K_S.gguf new file mode 100644 index 0000000..0759a64 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90c2f5cef8b9e55d3b3e9c47d23fcb359246be55dabcb5e24b4fba4297654b8 +size 2383308096 diff --git a/Qwen3-4B-Usefulness.Q5_K_M.gguf b/Qwen3-4B-Usefulness.Q5_K_M.gguf new file mode 100644 index 0000000..f9cdc57 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4787642be0fc492b7ff0f32540ba944cd17cb9f0b05629cf4e66bf20abaa6e +size 2889512256 diff --git a/Qwen3-4B-Usefulness.Q5_K_S.gguf b/Qwen3-4B-Usefulness.Q5_K_S.gguf new file mode 100644 index 0000000..f26a7d7 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038f74c0fd9b61a3ceea2d5e5e1abc55d36c03df2b2bba61cd3339acfbd27d2b +size 2823710016 diff --git a/Qwen3-4B-Usefulness.Q6_K.gguf b/Qwen3-4B-Usefulness.Q6_K.gguf new file mode 100644 index 0000000..4e8011d --- /dev/null +++ b/Qwen3-4B-Usefulness.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac69869c8cbc49cbcc750b0a7e1426227ce3c112fd0caa17736c13603cc992d3 +size 3306259776 diff --git a/Qwen3-4B-Usefulness.Q8_0.gguf b/Qwen3-4B-Usefulness.Q8_0.gguf new file mode 100644 index 0000000..c069bb5 --- /dev/null +++ b/Qwen3-4B-Usefulness.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0bab97e894a30e27bc75cb7d1cbfd1dde0fbcc7d0a13e0bd260e7f920c2d94 +size 4280403776 diff --git a/Qwen3-4B-Usefulness.f16.gguf b/Qwen3-4B-Usefulness.f16.gguf new file mode 100644 index 0000000..20d9855 --- /dev/null +++ b/Qwen3-4B-Usefulness.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4485cf16b7fb3e76fcc90620b4ba2a5b1533c84c5071aab2a508a3cffd6ab9ef +size 8051283776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..36ff2bf --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: miulab/Qwen3-4B-Usefulness +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/miulab/Qwen3-4B-Usefulness + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Usefulness-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/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Usefulness-GGUF/resolve/main/Qwen3-4B-Usefulness.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. + +