commit 6833531c01201640401b1c98ba3da2a1f7a2b94f Author: ModelHub XC Date: Thu Jul 9 22:34:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-MegaMerge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53f0e9f --- /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-MegaMerge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MegaMerge.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-MegaMerge.IQ4_XS.gguf b/Qwen3-4B-MegaMerge.IQ4_XS.gguf new file mode 100644 index 0000000..f3f2b4c --- /dev/null +++ b/Qwen3-4B-MegaMerge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3a03db61cc8b3226d869badf982de891daa1b77d260d72ed5b492185a3bdb5 +size 2492946208 diff --git a/Qwen3-4B-MegaMerge.Q2_K.gguf b/Qwen3-4B-MegaMerge.Q2_K.gguf new file mode 100644 index 0000000..f73e70e --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d47bec63879f728215c2cedc6f8dd60aa4dc3a618fb3b1ae1f101ebc2c36180 +size 1797122848 diff --git a/Qwen3-4B-MegaMerge.Q3_K_L.gguf b/Qwen3-4B-MegaMerge.Q3_K_L.gguf new file mode 100644 index 0000000..99dab83 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce326d49ae32384384217b72ca78ae73c902bef66c4716e457efb40c0b92a476 +size 2406912288 diff --git a/Qwen3-4B-MegaMerge.Q3_K_M.gguf b/Qwen3-4B-MegaMerge.Q3_K_M.gguf new file mode 100644 index 0000000..8503ce4 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a79bb9d50b3d637eb272e66ee003e61591fc1a427c40f618f01f3e027e5af3 +size 2242744608 diff --git a/Qwen3-4B-MegaMerge.Q3_K_S.gguf b/Qwen3-4B-MegaMerge.Q3_K_S.gguf new file mode 100644 index 0000000..908dac6 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abecb989154d01d228ceaa3c623d2d13c63d580ff56a989f25d1f1f9d55aadb +size 2054123808 diff --git a/Qwen3-4B-MegaMerge.Q4_K_M.gguf b/Qwen3-4B-MegaMerge.Q4_K_M.gguf new file mode 100644 index 0000000..643106c --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4c4e2cb2c7226b9622e28d04f3979ae7f2019ae76c285fba02da7866af617d +size 2716065568 diff --git a/Qwen3-4B-MegaMerge.Q4_K_S.gguf b/Qwen3-4B-MegaMerge.Q4_K_S.gguf new file mode 100644 index 0000000..585e375 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359cce03eb16b6d2cb2d8754e6a384411688153caf06625e80661a92d2e84afb +size 2602094368 diff --git a/Qwen3-4B-MegaMerge.Q5_K_M.gguf b/Qwen3-4B-MegaMerge.Q5_K_M.gguf new file mode 100644 index 0000000..0d96283 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffa252a54bca2b20103f1002923038f2a5982a1be1dcfef9b20c1432aaad1d9 +size 3156918048 diff --git a/Qwen3-4B-MegaMerge.Q5_K_S.gguf b/Qwen3-4B-MegaMerge.Q5_K_S.gguf new file mode 100644 index 0000000..f2d6b30 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f26713cc8b7284c057276b53ce849bfc873d62ee70de522d8a5562c1446a440 +size 3091115808 diff --git a/Qwen3-4B-MegaMerge.Q6_K.gguf b/Qwen3-4B-MegaMerge.Q6_K.gguf new file mode 100644 index 0000000..a3a0c70 --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea6a21c4023354b721f6078b1567b9d86688a3f63c0dd504426f9048ae83711 +size 3625323808 diff --git a/Qwen3-4B-MegaMerge.Q8_0.gguf b/Qwen3-4B-MegaMerge.Q8_0.gguf new file mode 100644 index 0000000..f09da7a --- /dev/null +++ b/Qwen3-4B-MegaMerge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516cbe40563190a53ad16231470518ec8df1ab9fdd73a733e860b337f68b6b42 +size 4693668128 diff --git a/Qwen3-4B-MegaMerge.f16.gguf b/Qwen3-4B-MegaMerge.f16.gguf new file mode 100644 index 0000000..d5fd230 --- /dev/null +++ b/Qwen3-4B-MegaMerge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98eb97342a07f26de096f9c6245ba990f650744657899306497e3247d320d976 +size 8829194528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4ec13c0 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: bunnycore/Qwen3-4B-MegaMerge +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-MegaMerge + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-MegaMerge-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-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-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MegaMerge-GGUF/resolve/main/Qwen3-4B-MegaMerge.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. + +