commit 07885d909f40fe82e2f9d67e85832dcae0cff050 Author: ModelHub XC Date: Wed Jul 22 02:16:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Bard-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59e7a37 --- /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-Bard.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Bard.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Bard.IQ4_XS.gguf b/Qwen3-4B-Bard.IQ4_XS.gguf new file mode 100644 index 0000000..202b826 --- /dev/null +++ b/Qwen3-4B-Bard.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1f3261d2b94ce6bca8f7dc5616e5f46ca318a97e0e2ae3f1fc0e67d4488cb8 +size 2286317152 diff --git a/Qwen3-4B-Bard.Q2_K.gguf b/Qwen3-4B-Bard.Q2_K.gguf new file mode 100644 index 0000000..5522931 --- /dev/null +++ b/Qwen3-4B-Bard.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aedfa9af99f6dc70dd927f879c78f6ddbab395b6dc9f749fedf156ecc5d0bb1 +size 1669500512 diff --git a/Qwen3-4B-Bard.Q3_K_L.gguf b/Qwen3-4B-Bard.Q3_K_L.gguf new file mode 100644 index 0000000..c003892 --- /dev/null +++ b/Qwen3-4B-Bard.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03956daae6cb23e5259c86e7c8d418beb12281399464703e2be85138f72626c +size 2239786592 diff --git a/Qwen3-4B-Bard.Q3_K_M.gguf b/Qwen3-4B-Bard.Q3_K_M.gguf new file mode 100644 index 0000000..3514b80 --- /dev/null +++ b/Qwen3-4B-Bard.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa0fe217406ffa2444730640b61c336861af211c73bf55900626e3d6e221f15d +size 2075618912 diff --git a/Qwen3-4B-Bard.Q3_K_S.gguf b/Qwen3-4B-Bard.Q3_K_S.gguf new file mode 100644 index 0000000..69ab3ce --- /dev/null +++ b/Qwen3-4B-Bard.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08820da9385a5a24ab94f316e8ce6fc0de2079002b0e26ac6d60a99470207e7a +size 1886998112 diff --git a/Qwen3-4B-Bard.Q4_K_M.gguf b/Qwen3-4B-Bard.Q4_K_M.gguf new file mode 100644 index 0000000..cb07411 --- /dev/null +++ b/Qwen3-4B-Bard.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec12b1f73ad392f0de8a0d60da452f0cc44215e3105489f71dd3e11f472f4286 +size 2497281632 diff --git a/Qwen3-4B-Bard.Q4_K_S.gguf b/Qwen3-4B-Bard.Q4_K_S.gguf new file mode 100644 index 0000000..953b78e --- /dev/null +++ b/Qwen3-4B-Bard.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2448574e786709cc655efdcd91329ac7dcef1f9486f2a890763360d54a0a040b +size 2383310432 diff --git a/Qwen3-4B-Bard.Q5_K_M.gguf b/Qwen3-4B-Bard.Q5_K_M.gguf new file mode 100644 index 0000000..fa4bd35 --- /dev/null +++ b/Qwen3-4B-Bard.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e66064891ccc3aea843998dde24cdd751df8e9d835c6a9e062e5bb490f1c03 +size 2889514592 diff --git a/Qwen3-4B-Bard.Q5_K_S.gguf b/Qwen3-4B-Bard.Q5_K_S.gguf new file mode 100644 index 0000000..f048d8c --- /dev/null +++ b/Qwen3-4B-Bard.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ba48a1a352251eb9e9995f482fe4e9397d23eb4afeb64b84980907acf01be6 +size 2823712352 diff --git a/Qwen3-4B-Bard.Q6_K.gguf b/Qwen3-4B-Bard.Q6_K.gguf new file mode 100644 index 0000000..c2acc45 --- /dev/null +++ b/Qwen3-4B-Bard.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1e604c3972a47bddb956dbbbd9c39a613fabedce4fc51fc9e92622ea6fc2f2 +size 3306262112 diff --git a/Qwen3-4B-Bard.Q8_0.gguf b/Qwen3-4B-Bard.Q8_0.gguf new file mode 100644 index 0000000..6539670 --- /dev/null +++ b/Qwen3-4B-Bard.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc06333ce94f9e98d2f66c39e5b29c7a0ca3579ac8d9911a1e297b240925382 +size 4280406112 diff --git a/Qwen3-4B-Bard.f16.gguf b/Qwen3-4B-Bard.f16.gguf new file mode 100644 index 0000000..48bf88f --- /dev/null +++ b/Qwen3-4B-Bard.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947c28e6d847d33b3acce03a7cca0228e13f4b448598b3e9a1d4ebcdcb131bfb +size 8051286112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a26df4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Lambent/Qwen3-4B-Bard +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Lambent/Qwen3-4B-Bard + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Bard-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Bard-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-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Bard-GGUF/resolve/main/Qwen3-4B-Bard.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. + +