commit e7031e2c6739ac9ff39fc8434c5069522c87db26 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-V3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e5288a6 --- /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-V3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-RP-V3.IQ4_XS.gguf b/Qwen3-4B-RP-V3.IQ4_XS.gguf new file mode 100644 index 0000000..f205afa --- /dev/null +++ b/Qwen3-4B-RP-V3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6dcec812cc147e1c7292dc1cebd736e752e60bc8442464fdcfcd8c6246a91cc +size 2286313440 diff --git a/Qwen3-4B-RP-V3.Q2_K.gguf b/Qwen3-4B-RP-V3.Q2_K.gguf new file mode 100644 index 0000000..7741cca --- /dev/null +++ b/Qwen3-4B-RP-V3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e244f64f3ddb105051956022d9f0f8597c64bd31f16fcd90b39a77f4433fc7a +size 1669496800 diff --git a/Qwen3-4B-RP-V3.Q3_K_L.gguf b/Qwen3-4B-RP-V3.Q3_K_L.gguf new file mode 100644 index 0000000..098cd09 --- /dev/null +++ b/Qwen3-4B-RP-V3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555737324437338d926894491dd8c3f8769ce253ce2467343ea815c8138c4e65 +size 2239782880 diff --git a/Qwen3-4B-RP-V3.Q3_K_M.gguf b/Qwen3-4B-RP-V3.Q3_K_M.gguf new file mode 100644 index 0000000..4076006 --- /dev/null +++ b/Qwen3-4B-RP-V3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed4fbe4dfd059bd4639f7e879d8fc3a59daed53279d05f5308862b6ae3cdbe2 +size 2075615200 diff --git a/Qwen3-4B-RP-V3.Q3_K_S.gguf b/Qwen3-4B-RP-V3.Q3_K_S.gguf new file mode 100644 index 0000000..367e69f --- /dev/null +++ b/Qwen3-4B-RP-V3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02208d973bcced1afded376ecce026bb6eef55df05a0bc55b1ed5a280ecf3dc3 +size 1886994400 diff --git a/Qwen3-4B-RP-V3.Q4_K_M.gguf b/Qwen3-4B-RP-V3.Q4_K_M.gguf new file mode 100644 index 0000000..c1824a5 --- /dev/null +++ b/Qwen3-4B-RP-V3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9be74153479a711f6a75fb818dc831079db9a903ec981397c462d5b28b51218 +size 2497277920 diff --git a/Qwen3-4B-RP-V3.Q4_K_S.gguf b/Qwen3-4B-RP-V3.Q4_K_S.gguf new file mode 100644 index 0000000..9c730d8 --- /dev/null +++ b/Qwen3-4B-RP-V3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed093ba4e0e23026fdb47e61921870c03f4c4b8c8ef68202adb2e9fe8e230aa +size 2383306720 diff --git a/Qwen3-4B-RP-V3.Q5_K_M.gguf b/Qwen3-4B-RP-V3.Q5_K_M.gguf new file mode 100644 index 0000000..163802e --- /dev/null +++ b/Qwen3-4B-RP-V3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d2e503a3f9ec65e26613d0e0b95335e76db7add23b739c837710098e349c36 +size 2889510880 diff --git a/Qwen3-4B-RP-V3.Q5_K_S.gguf b/Qwen3-4B-RP-V3.Q5_K_S.gguf new file mode 100644 index 0000000..c6bdffc --- /dev/null +++ b/Qwen3-4B-RP-V3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbedf10c9ec22833632bc202db37ca7058aafa26c0165031cdf4032010ff151 +size 2823708640 diff --git a/Qwen3-4B-RP-V3.Q6_K.gguf b/Qwen3-4B-RP-V3.Q6_K.gguf new file mode 100644 index 0000000..bfba3fc --- /dev/null +++ b/Qwen3-4B-RP-V3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01467ad105a17ca614f219eb3b44c22ef8ef0243013960aa59a52e6ab962364 +size 3306258400 diff --git a/Qwen3-4B-RP-V3.Q8_0.gguf b/Qwen3-4B-RP-V3.Q8_0.gguf new file mode 100644 index 0000000..3dedd17 --- /dev/null +++ b/Qwen3-4B-RP-V3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e080b1e535763a85886be0f7ef959c9903f8744cde13948f4ed82022bd1912 +size 4280402400 diff --git a/Qwen3-4B-RP-V3.f16.gguf b/Qwen3-4B-RP-V3.f16.gguf new file mode 100644 index 0000000..d585c11 --- /dev/null +++ b/Qwen3-4B-RP-V3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c13010abfef714d9064928816b81863c55c03d4f2a327c9f763097260ea3b0 +size 8051282400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..78aa8b8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bunnycore/Qwen3-4B-RP-V3 +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-V3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-RP-V3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-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-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V3-GGUF/resolve/main/Qwen3-4B-RP-V3.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. + +