commit ad1a28bdbd51ccd1b9ae2a611b24f26f9a495604 Author: ModelHub XC Date: Wed Jul 22 14:50:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Exp2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e13b6a4 --- /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-Exp2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Exp2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Exp2.IQ4_XS.gguf b/Qwen3-4B-Exp2.IQ4_XS.gguf new file mode 100644 index 0000000..a10c8b2 --- /dev/null +++ b/Qwen3-4B-Exp2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d5642558bdf2de6753ef510f61db6d9607bdcfeff8f78c956571b6643356bb +size 2492945312 diff --git a/Qwen3-4B-Exp2.Q2_K.gguf b/Qwen3-4B-Exp2.Q2_K.gguf new file mode 100644 index 0000000..6d737e3 --- /dev/null +++ b/Qwen3-4B-Exp2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df92c8abde0c0285ae6578bee8c832d81edf21d9e10ac052a64544b5e855e91c +size 1797121952 diff --git a/Qwen3-4B-Exp2.Q3_K_L.gguf b/Qwen3-4B-Exp2.Q3_K_L.gguf new file mode 100644 index 0000000..7a64e87 --- /dev/null +++ b/Qwen3-4B-Exp2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a42238319a5a017d872535610d5e4044d054798091c69190e2457e355f86172 +size 2406911392 diff --git a/Qwen3-4B-Exp2.Q3_K_M.gguf b/Qwen3-4B-Exp2.Q3_K_M.gguf new file mode 100644 index 0000000..4376c71 --- /dev/null +++ b/Qwen3-4B-Exp2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c913c4b843f8fe2959a3bc5ae8599a7fed8c960b9a6a19647ae0421fa7abcc +size 2242743712 diff --git a/Qwen3-4B-Exp2.Q3_K_S.gguf b/Qwen3-4B-Exp2.Q3_K_S.gguf new file mode 100644 index 0000000..8194059 --- /dev/null +++ b/Qwen3-4B-Exp2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6977acdfb9f68a15fd68f08efeeb3d7f5ac8b5e6fb7b2f5e071d78221b102046 +size 2054122912 diff --git a/Qwen3-4B-Exp2.Q4_K_M.gguf b/Qwen3-4B-Exp2.Q4_K_M.gguf new file mode 100644 index 0000000..0862075 --- /dev/null +++ b/Qwen3-4B-Exp2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40119b9b4f5d07d2d40e4660426680a3534cafaf650a087aac699161c359ffd +size 2716064672 diff --git a/Qwen3-4B-Exp2.Q4_K_S.gguf b/Qwen3-4B-Exp2.Q4_K_S.gguf new file mode 100644 index 0000000..f128672 --- /dev/null +++ b/Qwen3-4B-Exp2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df562fba626d5e2781703025926ab27d843b291ca3e0788d5df0e3ac036f994a +size 2602093472 diff --git a/Qwen3-4B-Exp2.Q5_K_M.gguf b/Qwen3-4B-Exp2.Q5_K_M.gguf new file mode 100644 index 0000000..937223e --- /dev/null +++ b/Qwen3-4B-Exp2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda508ad55d7fdb96a58e637e909ea2fcaff3a57f4316c8b09a4413d30315716 +size 3156917152 diff --git a/Qwen3-4B-Exp2.Q5_K_S.gguf b/Qwen3-4B-Exp2.Q5_K_S.gguf new file mode 100644 index 0000000..76f5c76 --- /dev/null +++ b/Qwen3-4B-Exp2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:971df0257983063f215143b5a8167475b7e573dc29ac1d489c8d626482d70988 +size 3091114912 diff --git a/Qwen3-4B-Exp2.Q6_K.gguf b/Qwen3-4B-Exp2.Q6_K.gguf new file mode 100644 index 0000000..a31dc70 --- /dev/null +++ b/Qwen3-4B-Exp2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a94bb84ebfadcdd7380dc37acf7ade46f44fe111fc97a49c5cd3d202f3f442 +size 3625322912 diff --git a/Qwen3-4B-Exp2.Q8_0.gguf b/Qwen3-4B-Exp2.Q8_0.gguf new file mode 100644 index 0000000..688754f --- /dev/null +++ b/Qwen3-4B-Exp2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5166050169e029834cd9b674df8ac1a71a1bba97aa5076e1241e819f57ee272 +size 4693667232 diff --git a/Qwen3-4B-Exp2.f16.gguf b/Qwen3-4B-Exp2.f16.gguf new file mode 100644 index 0000000..95dcf63 --- /dev/null +++ b/Qwen3-4B-Exp2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fa1428cc649d983645a03c84d2f279250fcdedbece438f55a6230e7175ac19 +size 8829193632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fb57dc --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: bunnycore/Qwen3-4B-Exp2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- beyoru/Qwen3-4B-I-1509 +- TeichAI/Qwen3-4B-Instruct-2507-Claude-Opus-3-Distill +- bunnycore/Qwen3-4B-Exp +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Exp2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Exp2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Exp2-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-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Exp2-GGUF/resolve/main/Qwen3-4B-Exp2.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. + +