commit e6b5374e8bce56f09c15d1608db802dcf57a7b2e Author: ModelHub XC Date: Sat Apr 18 21:23:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Max-Merge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd70869 --- /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-Merge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Max-Merge.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Max-Merge.IQ4_XS.gguf b/Qwen3-4B-Max-Merge.IQ4_XS.gguf new file mode 100644 index 0000000..a672c44 --- /dev/null +++ b/Qwen3-4B-Max-Merge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a69dbe79d8cba58908985697ce36ff50db9791e6cee68aa0d1b2dd1d6617e6 +size 2492946208 diff --git a/Qwen3-4B-Max-Merge.Q2_K.gguf b/Qwen3-4B-Max-Merge.Q2_K.gguf new file mode 100644 index 0000000..ac9bec8 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06d7a022682e718b1f2dea6dca051abbc9a1ceb5a7ccf27a11fc43cae0622a8 +size 1797122848 diff --git a/Qwen3-4B-Max-Merge.Q3_K_L.gguf b/Qwen3-4B-Max-Merge.Q3_K_L.gguf new file mode 100644 index 0000000..bf32652 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01daa5bb881babae413082d6d4bf9b4107eba13c0d84e68810892fa2d5002a9 +size 2406912288 diff --git a/Qwen3-4B-Max-Merge.Q3_K_M.gguf b/Qwen3-4B-Max-Merge.Q3_K_M.gguf new file mode 100644 index 0000000..a0eb77a --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de0eaca8e2175126f30c2566d8fc34b914571eca691c31677c978f0dc5fe141 +size 2242744608 diff --git a/Qwen3-4B-Max-Merge.Q3_K_S.gguf b/Qwen3-4B-Max-Merge.Q3_K_S.gguf new file mode 100644 index 0000000..413cddd --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f46ab8fdfedb1951d363702e0e7e4b5f7574ac80426a5cb75db0b5c1f620e9 +size 2054123808 diff --git a/Qwen3-4B-Max-Merge.Q4_K_M.gguf b/Qwen3-4B-Max-Merge.Q4_K_M.gguf new file mode 100644 index 0000000..5d696c1 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f90f2e2a15e23c2d574310e84de4c0f78300e99f52f34e0122898b6f4c9be7 +size 2716065568 diff --git a/Qwen3-4B-Max-Merge.Q4_K_S.gguf b/Qwen3-4B-Max-Merge.Q4_K_S.gguf new file mode 100644 index 0000000..af9d4a2 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bfa9ea64d15f18db324aea293f3974959522749bf01a6ed50d423afe022d13 +size 2602094368 diff --git a/Qwen3-4B-Max-Merge.Q5_K_M.gguf b/Qwen3-4B-Max-Merge.Q5_K_M.gguf new file mode 100644 index 0000000..915536c --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6613b939c418f1b06c5f7212bc00119c249e79052119fe828d39d1dad7b3470 +size 3156918048 diff --git a/Qwen3-4B-Max-Merge.Q5_K_S.gguf b/Qwen3-4B-Max-Merge.Q5_K_S.gguf new file mode 100644 index 0000000..73fea89 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d925c84d51deaa51f1c4f4719fbae7d12f06d6fdfba3ce808bd127fcca23fb +size 3091115808 diff --git a/Qwen3-4B-Max-Merge.Q6_K.gguf b/Qwen3-4B-Max-Merge.Q6_K.gguf new file mode 100644 index 0000000..79fcbf1 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3123fd9b0f45f69f07630e5c99649071a7e909078d14b21798ef1f46e62b8f1d +size 3625323808 diff --git a/Qwen3-4B-Max-Merge.Q8_0.gguf b/Qwen3-4B-Max-Merge.Q8_0.gguf new file mode 100644 index 0000000..9dbaaf4 --- /dev/null +++ b/Qwen3-4B-Max-Merge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe79286dd35e5aa52d7f6ece035a688aeba924125399beed02f979ebf496947 +size 4693668128 diff --git a/Qwen3-4B-Max-Merge.f16.gguf b/Qwen3-4B-Max-Merge.f16.gguf new file mode 100644 index 0000000..130fa6f --- /dev/null +++ b/Qwen3-4B-Max-Merge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ea9824fa0c97527ed82c7bde23fc9fc1c4272831d16a50808149a2e2d033c0 +size 8829194528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c0172b --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: bunnycore/Qwen3-4B-Max-Merge +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- bunnycore/Qwen3-4B-Max-Ties +- SamuelBang/AesCoder-4B +- Pinkstack/DistilGPT-OSS-qwen3-4B +- minchyeom/Qwaifu +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Max-Merge + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Max-Merge-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-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-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Max-Merge-GGUF/resolve/main/Qwen3-4B-Max-Merge.f16.gguf) | f16 | 8.9 | 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. + +