commit adc6bf24353cb7bd04e199a20818fec1a9483679 Author: ModelHub XC Date: Wed Jun 3 05:32:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Steer-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7708d68 --- /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-Steer.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Steer.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Steer.IQ4_XS.gguf b/Qwen3-4B-Steer.IQ4_XS.gguf new file mode 100644 index 0000000..3588aa5 --- /dev/null +++ b/Qwen3-4B-Steer.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10f7618b5deaba3a1df387f7da4aedbf71de0cde1d3d5d462bee85535f7f14a +size 2286312192 diff --git a/Qwen3-4B-Steer.Q2_K.gguf b/Qwen3-4B-Steer.Q2_K.gguf new file mode 100644 index 0000000..9a0916e --- /dev/null +++ b/Qwen3-4B-Steer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccef9c26f65237deff72a610911a34923029c7b15bf1b2ebe7fc8f8426bb2aa +size 1669495552 diff --git a/Qwen3-4B-Steer.Q3_K_L.gguf b/Qwen3-4B-Steer.Q3_K_L.gguf new file mode 100644 index 0000000..83c3120 --- /dev/null +++ b/Qwen3-4B-Steer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d3343cae33289d5f74d1cd1204f6b33a15d1a64b891b66de3f33b21f4b9ba5 +size 2239781632 diff --git a/Qwen3-4B-Steer.Q3_K_M.gguf b/Qwen3-4B-Steer.Q3_K_M.gguf new file mode 100644 index 0000000..00b0649 --- /dev/null +++ b/Qwen3-4B-Steer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7fa4cfec792465bd6b43469e4558b1a58a0b34c08408d013cac55115299193 +size 2075613952 diff --git a/Qwen3-4B-Steer.Q3_K_S.gguf b/Qwen3-4B-Steer.Q3_K_S.gguf new file mode 100644 index 0000000..8d89cee --- /dev/null +++ b/Qwen3-4B-Steer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f163c09371fd2e2a22bba9e7dbef7d70552e5a2fd62b9e8b399b119d897aefdd +size 1886993152 diff --git a/Qwen3-4B-Steer.Q4_K_M.gguf b/Qwen3-4B-Steer.Q4_K_M.gguf new file mode 100644 index 0000000..23cb3f3 --- /dev/null +++ b/Qwen3-4B-Steer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08068059be2c46af35d7d817f2aa88c57e7cfdfe1d58af5b7b4b576faefdfabc +size 2497276672 diff --git a/Qwen3-4B-Steer.Q4_K_S.gguf b/Qwen3-4B-Steer.Q4_K_S.gguf new file mode 100644 index 0000000..5afdba1 --- /dev/null +++ b/Qwen3-4B-Steer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c1aaeddb08f24131322aae21724e54436f1f11df3cbcbcb8556eeb1f7c94da +size 2383305472 diff --git a/Qwen3-4B-Steer.Q5_K_M.gguf b/Qwen3-4B-Steer.Q5_K_M.gguf new file mode 100644 index 0000000..0a9a53a --- /dev/null +++ b/Qwen3-4B-Steer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bf1bcd290a2dbaa5a995ae124ebf110e607ecf7422500e3b40fe70f2b5f606 +size 2889509632 diff --git a/Qwen3-4B-Steer.Q5_K_S.gguf b/Qwen3-4B-Steer.Q5_K_S.gguf new file mode 100644 index 0000000..81a7e55 --- /dev/null +++ b/Qwen3-4B-Steer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872fcc8443844adb9c7bbff9b551920786265a85e2506aef9124e8470583186b +size 2823707392 diff --git a/Qwen3-4B-Steer.Q6_K.gguf b/Qwen3-4B-Steer.Q6_K.gguf new file mode 100644 index 0000000..da60523 --- /dev/null +++ b/Qwen3-4B-Steer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a574fec31596b6df4ce5ffbb8e0a9de3deec48b873946193ea96d0a3070ee3 +size 3306257152 diff --git a/Qwen3-4B-Steer.Q8_0.gguf b/Qwen3-4B-Steer.Q8_0.gguf new file mode 100644 index 0000000..e276dee --- /dev/null +++ b/Qwen3-4B-Steer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7fde1774d8870ce457f3f43ef3a0a08d03243d84eb16c2d5caa9db5a49c8b21 +size 4280401152 diff --git a/Qwen3-4B-Steer.f16.gguf b/Qwen3-4B-Steer.f16.gguf new file mode 100644 index 0000000..029ca05 --- /dev/null +++ b/Qwen3-4B-Steer.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f8fda659da00978cbc98de751fdb1d3c929bdafcb70dc8f83fed4513b52c919 +size 8051281152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d3748ca --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: bunnycore/Qwen3-4B-Steer +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen3-4B-Steer + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Steer-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Steer-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-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Steer-GGUF/resolve/main/Qwen3-4B-Steer.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. + +