commit 803e813b2bc89f7cfc9aa4ba636808e433a9f880 Author: ModelHub XC Date: Mon May 25 16:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ac5dc0 --- /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-RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-RP.IQ4_XS.gguf b/Qwen3-4B-RP.IQ4_XS.gguf new file mode 100644 index 0000000..bbb55da --- /dev/null +++ b/Qwen3-4B-RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbdcce757964d7d92a47e484778502acb8a7733d3933d995ab153e2f267474a +size 2286312864 diff --git a/Qwen3-4B-RP.Q2_K.gguf b/Qwen3-4B-RP.Q2_K.gguf new file mode 100644 index 0000000..d5c49bf --- /dev/null +++ b/Qwen3-4B-RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fac2eb1b5ed3a9069f692b067d7f64bec536d0bd3f66956cabf15ca27bad6cb +size 1669496224 diff --git a/Qwen3-4B-RP.Q3_K_L.gguf b/Qwen3-4B-RP.Q3_K_L.gguf new file mode 100644 index 0000000..012bb37 --- /dev/null +++ b/Qwen3-4B-RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f5e22b137755590ef27f81ab2e6a9d1b69ce3c2a8b598fa778b42570ea2f19 +size 2239782304 diff --git a/Qwen3-4B-RP.Q3_K_M.gguf b/Qwen3-4B-RP.Q3_K_M.gguf new file mode 100644 index 0000000..1f8c295 --- /dev/null +++ b/Qwen3-4B-RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34059ab019e1c4ed76ea222b4232f9b5cc91c9dfc5f790a411465e90d0b3f04c +size 2075614624 diff --git a/Qwen3-4B-RP.Q3_K_S.gguf b/Qwen3-4B-RP.Q3_K_S.gguf new file mode 100644 index 0000000..73c807c --- /dev/null +++ b/Qwen3-4B-RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6677096db756e10af8e062937621e58bbed12ae14cbb52d7e354875a03b0929 +size 1886993824 diff --git a/Qwen3-4B-RP.Q4_K_M.gguf b/Qwen3-4B-RP.Q4_K_M.gguf new file mode 100644 index 0000000..8bc5f17 --- /dev/null +++ b/Qwen3-4B-RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd934eb10470228750051ae04e16634fd962e43d89df4c5723dc93114c41d1d7 +size 2497277344 diff --git a/Qwen3-4B-RP.Q4_K_S.gguf b/Qwen3-4B-RP.Q4_K_S.gguf new file mode 100644 index 0000000..316bdad --- /dev/null +++ b/Qwen3-4B-RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abcd040af3254d46dc1e0553c93a4e110c6e67909035feb1532d35d5a97943a +size 2383306144 diff --git a/Qwen3-4B-RP.Q5_K_M.gguf b/Qwen3-4B-RP.Q5_K_M.gguf new file mode 100644 index 0000000..da37796 --- /dev/null +++ b/Qwen3-4B-RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dbc963ec667d808b7690330f8196579c9a0be671ac19b63fc7f762308e0c10 +size 2889510304 diff --git a/Qwen3-4B-RP.Q5_K_S.gguf b/Qwen3-4B-RP.Q5_K_S.gguf new file mode 100644 index 0000000..8838d4e --- /dev/null +++ b/Qwen3-4B-RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab0fb1a982f5969be83738ad7de30c72adf6ff2effe00731698665120061b43 +size 2823708064 diff --git a/Qwen3-4B-RP.Q6_K.gguf b/Qwen3-4B-RP.Q6_K.gguf new file mode 100644 index 0000000..4734f96 --- /dev/null +++ b/Qwen3-4B-RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14eb88fc998e0b710cf2cae3da81fe96b80caeb0d14a323bf9ff640d355e658f +size 3306257824 diff --git a/Qwen3-4B-RP.Q8_0.gguf b/Qwen3-4B-RP.Q8_0.gguf new file mode 100644 index 0000000..6643a96 --- /dev/null +++ b/Qwen3-4B-RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e47e1f77466e743cb9fc35ac26aafbdddff8c503a9fa4cf2b068e834e37ce7 +size 4280401824 diff --git a/Qwen3-4B-RP.f16.gguf b/Qwen3-4B-RP.f16.gguf new file mode 100644 index 0000000..aec76d2 --- /dev/null +++ b/Qwen3-4B-RP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ef3dafa9042514af66ffee0207cc84363d4df3054f6ad977943901cecc79b7 +size 8051281824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce6ec66 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bunnycore/Qwen3-4B-RP +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-RP + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-RP-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-RP-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-RP-GGUF/resolve/main/Qwen3-4B-RP.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-GGUF/resolve/main/Qwen3-4B-RP.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. + +