commit 5f09f394cc255fd995cd242af7e0efb08391d6fd Author: ModelHub XC Date: Mon Jul 13 03:41:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8855020 --- /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-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Base.IQ4_XS.gguf b/Qwen3-4B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..f609af4 --- /dev/null +++ b/Qwen3-4B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e2ee5d161ab7d7c5f8380121b0a519ba6b61177b3ffb451c8c95feb69b5163 +size 2286316256 diff --git a/Qwen3-4B-Base.Q2_K.gguf b/Qwen3-4B-Base.Q2_K.gguf new file mode 100644 index 0000000..5976bbb --- /dev/null +++ b/Qwen3-4B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ec04cf198acd5ab34636a960ba8e27cb244c7e777413cf3f9d8d19c477bf92 +size 1669499616 diff --git a/Qwen3-4B-Base.Q3_K_L.gguf b/Qwen3-4B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..607dfc0 --- /dev/null +++ b/Qwen3-4B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0d383326747a31192dc2b816caca17b27e0dbfa5e4a7187a0a30b536e32a7b +size 2239785696 diff --git a/Qwen3-4B-Base.Q3_K_M.gguf b/Qwen3-4B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..c568557 --- /dev/null +++ b/Qwen3-4B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3699e49319e549848581b07de65b8b14715c37bc8ccc2b834af1ee0df49366f8 +size 2075618016 diff --git a/Qwen3-4B-Base.Q3_K_S.gguf b/Qwen3-4B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..5961dda --- /dev/null +++ b/Qwen3-4B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b6afe6da580081d672b381d0e15916ffc22005190ccb088e46ae9ccdb5708e +size 1886997216 diff --git a/Qwen3-4B-Base.Q4_K_M.gguf b/Qwen3-4B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..92c8a07 --- /dev/null +++ b/Qwen3-4B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7eb1d92eaf34e116f8b522aeeaf4072e66d69b5b10676e0cb7cd9e11889bed6 +size 2497280736 diff --git a/Qwen3-4B-Base.Q4_K_S.gguf b/Qwen3-4B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..93bc506 --- /dev/null +++ b/Qwen3-4B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ea886b5217152ad488f7b7585b7b8fe33a69dec89bdf0c27b60327b4558f8a +size 2383309536 diff --git a/Qwen3-4B-Base.Q5_K_M.gguf b/Qwen3-4B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..e93f269 --- /dev/null +++ b/Qwen3-4B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699936b83664f71a4c1d129a1e10b02c1909e8edfdd32962cea75259f4f92093 +size 2889513696 diff --git a/Qwen3-4B-Base.Q5_K_S.gguf b/Qwen3-4B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..f31a9ee --- /dev/null +++ b/Qwen3-4B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0b0117a0b884adeff4f7fede3b39bb1b03e8824ec7aeef309918bb0aae913a +size 2823711456 diff --git a/Qwen3-4B-Base.Q6_K.gguf b/Qwen3-4B-Base.Q6_K.gguf new file mode 100644 index 0000000..a4acc03 --- /dev/null +++ b/Qwen3-4B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdab7d0668c0319116413caa0990e5d98a1f64cd6d41bc1ec608eb0d25f55dd +size 3306261216 diff --git a/Qwen3-4B-Base.Q8_0.gguf b/Qwen3-4B-Base.Q8_0.gguf new file mode 100644 index 0000000..b9fd96c --- /dev/null +++ b/Qwen3-4B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4498bfc249d7597bef6e4bff1637c4cb9c6434974cada81b68a26974e23be977 +size 4280405216 diff --git a/Qwen3-4B-Base.f16.gguf b/Qwen3-4B-Base.f16.gguf new file mode 100644 index 0000000..6f595e9 --- /dev/null +++ b/Qwen3-4B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860a78636750428e98321e859afbef487a5d31f1545ce261d0f74eed412da173 +size 8051285216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdf25db --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Qwen/Qwen3-4B-Base +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-4B-Base + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Base-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-Base-GGUF/resolve/main/Qwen3-4B-Base.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-GGUF/resolve/main/Qwen3-4B-Base.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. + +