commit 4230bd7b2b0c685e451884cb8669433e33ce7865 Author: ModelHub XC Date: Mon May 25 16:11:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-RP-V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a2e5354 --- /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-V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-RP-V2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-RP-V2.IQ4_XS.gguf b/Qwen3-4B-RP-V2.IQ4_XS.gguf new file mode 100644 index 0000000..bf83af2 --- /dev/null +++ b/Qwen3-4B-RP-V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfb0a7bf17fab6ba0a0ef026368ac80caf2c2dae5e0a761f4e06eb8ff93bbfb +size 2286317280 diff --git a/Qwen3-4B-RP-V2.Q2_K.gguf b/Qwen3-4B-RP-V2.Q2_K.gguf new file mode 100644 index 0000000..3ea7409 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d49cd09a28c29ba5759004dd0defc26f17584adf9cdb4e6bf5beb9e873ce51 +size 1669500640 diff --git a/Qwen3-4B-RP-V2.Q3_K_L.gguf b/Qwen3-4B-RP-V2.Q3_K_L.gguf new file mode 100644 index 0000000..ca038ca --- /dev/null +++ b/Qwen3-4B-RP-V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f520b87041f6e2a00b6889dca264a1ed8696aead630d860ce17d53ad7ed95599 +size 2239786720 diff --git a/Qwen3-4B-RP-V2.Q3_K_M.gguf b/Qwen3-4B-RP-V2.Q3_K_M.gguf new file mode 100644 index 0000000..6a52eaa --- /dev/null +++ b/Qwen3-4B-RP-V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b2602c50c5a6728bd85e30356b14dd2fc9e8d42520db15dd40f56c58615584 +size 2075619040 diff --git a/Qwen3-4B-RP-V2.Q3_K_S.gguf b/Qwen3-4B-RP-V2.Q3_K_S.gguf new file mode 100644 index 0000000..1edce77 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34498274c3e47fcdbca9da9c4c18742635c7a472b2f4df3cb5652d567d98fcad +size 1886998240 diff --git a/Qwen3-4B-RP-V2.Q4_K_M.gguf b/Qwen3-4B-RP-V2.Q4_K_M.gguf new file mode 100644 index 0000000..6542822 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124ba09cc31bd00ef50b87fc8025c1d6e54287107c1e1ce067a6a334f870f288 +size 2497281760 diff --git a/Qwen3-4B-RP-V2.Q4_K_S.gguf b/Qwen3-4B-RP-V2.Q4_K_S.gguf new file mode 100644 index 0000000..833e82d --- /dev/null +++ b/Qwen3-4B-RP-V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0352e80766d751e1015bd7327673b1be3c7e586045ce31d74d91064f2e7a4d9d +size 2383310560 diff --git a/Qwen3-4B-RP-V2.Q5_K_M.gguf b/Qwen3-4B-RP-V2.Q5_K_M.gguf new file mode 100644 index 0000000..7fe0e69 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c666f65f2339227071e69b7c39c1cd97f5b914ac41a79f9038a74c68a2d83602 +size 2889514720 diff --git a/Qwen3-4B-RP-V2.Q5_K_S.gguf b/Qwen3-4B-RP-V2.Q5_K_S.gguf new file mode 100644 index 0000000..7288192 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f71133331ff83db19fdf714e6608d0dc10d50f01ca3bff1d8ea4012a2994ebe +size 2823712480 diff --git a/Qwen3-4B-RP-V2.Q6_K.gguf b/Qwen3-4B-RP-V2.Q6_K.gguf new file mode 100644 index 0000000..ad25554 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd11aa54962f036ba7e9d994051379b163dd1edfd8b7a62bc181709061cda8d5 +size 3306262240 diff --git a/Qwen3-4B-RP-V2.Q8_0.gguf b/Qwen3-4B-RP-V2.Q8_0.gguf new file mode 100644 index 0000000..0ca61c0 --- /dev/null +++ b/Qwen3-4B-RP-V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a568bd396ed2ec4fd97fb909c2c2af0a5eaabff0a1a37df8f145c6f2e2addb0a +size 4280406240 diff --git a/Qwen3-4B-RP-V2.f16.gguf b/Qwen3-4B-RP-V2.f16.gguf new file mode 100644 index 0000000..86db802 --- /dev/null +++ b/Qwen3-4B-RP-V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5ab81a3e3f5620290dc363329dd386b6f7657518fe967d7cd21769b157d0c7 +size 8051286240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..84f1c3e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bunnycore/Qwen3-4B-RP-V2 +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-V2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-RP-V2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-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-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-RP-V2-GGUF/resolve/main/Qwen3-4B-RP-V2.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. + +