commit fd95c44c2ddcdbc7cfe37fc955494a66ee7fc320 Author: ModelHub XC Date: Mon Jun 1 17:59:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Max-Ties-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..178cd3a --- /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-Max-Ties.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Ties.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Max-Ties.IQ4_XS.gguf b/Qwen3-4B-Max-Ties.IQ4_XS.gguf new file mode 100644 index 0000000..9f86565 --- /dev/null +++ b/Qwen3-4B-Max-Ties.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be244841a6575b28d3e70d5033a229d142a43cbc963ee2c08db865e04401915 +size 2286313088 diff --git a/Qwen3-4B-Max-Ties.Q2_K.gguf b/Qwen3-4B-Max-Ties.Q2_K.gguf new file mode 100644 index 0000000..8d952e8 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cdecc71d6db37d21956afe18585c51a9195c4d9fb5b01953c5f9d5af841ee0 +size 1669496448 diff --git a/Qwen3-4B-Max-Ties.Q3_K_L.gguf b/Qwen3-4B-Max-Ties.Q3_K_L.gguf new file mode 100644 index 0000000..9e63bdb --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880a802ec851961482fcdd1d4dc81e159f7cea4392b1074028794c7ba29c3f00 +size 2239782528 diff --git a/Qwen3-4B-Max-Ties.Q3_K_M.gguf b/Qwen3-4B-Max-Ties.Q3_K_M.gguf new file mode 100644 index 0000000..957ac22 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5d7789de0b15576e8728ee30cb45e46d6b282b293bf5185515c38eec71f187 +size 2075614848 diff --git a/Qwen3-4B-Max-Ties.Q3_K_S.gguf b/Qwen3-4B-Max-Ties.Q3_K_S.gguf new file mode 100644 index 0000000..dd902c6 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363b5e503058bf42e5d8dc9b24735604efdfd059d228b412c7f915650879c96e +size 1886994048 diff --git a/Qwen3-4B-Max-Ties.Q4_K_M.gguf b/Qwen3-4B-Max-Ties.Q4_K_M.gguf new file mode 100644 index 0000000..f9fdfb4 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68a53abdbebae96dddc0245ec36e15c5d0398c6d3e900c3ab32fdd86e54f8a1 +size 2497277568 diff --git a/Qwen3-4B-Max-Ties.Q4_K_S.gguf b/Qwen3-4B-Max-Ties.Q4_K_S.gguf new file mode 100644 index 0000000..639e900 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0664b05e830a98d4f87988161d58fc162c1f180d2b714111339f035d8f19eeb +size 2383306368 diff --git a/Qwen3-4B-Max-Ties.Q5_K_M.gguf b/Qwen3-4B-Max-Ties.Q5_K_M.gguf new file mode 100644 index 0000000..c9561c6 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc82fa29eac22d4013cb4abee67b36bea8a5c9e47a187713b93276a16bf2f3b0 +size 2889510528 diff --git a/Qwen3-4B-Max-Ties.Q5_K_S.gguf b/Qwen3-4B-Max-Ties.Q5_K_S.gguf new file mode 100644 index 0000000..adda6ca --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8278d8b006a291b7b864452e62c887ee45d4765979c91f7d2b359064977614b5 +size 2823708288 diff --git a/Qwen3-4B-Max-Ties.Q6_K.gguf b/Qwen3-4B-Max-Ties.Q6_K.gguf new file mode 100644 index 0000000..3ece6aa --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41aad0dc47521d80d42db823b6feada5b0025f1c15ea8a67502a89df88437cf +size 3306258048 diff --git a/Qwen3-4B-Max-Ties.Q8_0.gguf b/Qwen3-4B-Max-Ties.Q8_0.gguf new file mode 100644 index 0000000..e440036 --- /dev/null +++ b/Qwen3-4B-Max-Ties.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b639ebc4c48bee16074a2959dd55b229b1e8f1da1124ef49f312651be1859999 +size 4280402048 diff --git a/Qwen3-4B-Max-Ties.f16.gguf b/Qwen3-4B-Max-Ties.f16.gguf new file mode 100644 index 0000000..572595a --- /dev/null +++ b/Qwen3-4B-Max-Ties.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4545bc0f1de101570568710ecc2b1ebbf2dacc6521fec840c2b176913230796d +size 8051282048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..20b1627 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: bunnycore/Qwen3-4B-Max-Ties +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- janhq/Jan-v1-2509 +- huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated +- minchyeom/Qwaifu +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Max-Ties + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Max-Ties-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-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/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Ties-GGUF/resolve/main/Qwen3-4B-Max-Ties.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. + +