commit c80584518083c8dfb8b479b05e26246011d76739 Author: ModelHub XC Date: Mon Apr 27 06:51:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1d7e5d3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen1.5-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-4B.IQ4_XS.gguf b/Qwen1.5-4B.IQ4_XS.gguf new file mode 100644 index 0000000..2785773 --- /dev/null +++ b/Qwen1.5-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3fdc40636c732bd0125a81038d87d36130553a612744aad4aa8422d1028d20 +size 2232632384 diff --git a/Qwen1.5-4B.Q2_K.gguf b/Qwen1.5-4B.Q2_K.gguf new file mode 100644 index 0000000..3701eb5 --- /dev/null +++ b/Qwen1.5-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68efb5989a2c4b36d525019a75ec1d8ce848777789be45222a1cf0ed8269f4c4 +size 1620633664 diff --git a/Qwen1.5-4B.Q3_K_L.gguf b/Qwen1.5-4B.Q3_K_L.gguf new file mode 100644 index 0000000..e10b389 --- /dev/null +++ b/Qwen1.5-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8592d5f58daf2e02684dd33bb826e229b90b0c091fb21d032402b77d1b85a916 +size 2174799424 diff --git a/Qwen1.5-4B.Q3_K_M.gguf b/Qwen1.5-4B.Q3_K_M.gguf new file mode 100644 index 0000000..5749b08 --- /dev/null +++ b/Qwen1.5-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8cc87664acbf5d8f4c70e04cbe3a3d592c75444f769827010ed293f8edd22aa +size 2026851904 diff --git a/Qwen1.5-4B.Q3_K_S.gguf b/Qwen1.5-4B.Q3_K_S.gguf new file mode 100644 index 0000000..dcde91c --- /dev/null +++ b/Qwen1.5-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c34bdf09124091b791a6bc010fff1d7475d2a71912abc0408d811d6df8f9bb +size 1857154624 diff --git a/Qwen1.5-4B.Q4_0_4_4.gguf b/Qwen1.5-4B.Q4_0_4_4.gguf new file mode 100644 index 0000000..1c45f1e --- /dev/null +++ b/Qwen1.5-4B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7370d97254983d2b2dbf3950dcb3bac5623fdd706f8c216339433461d30f6a16 +size 2330086464 diff --git a/Qwen1.5-4B.Q4_K_M.gguf b/Qwen1.5-4B.Q4_K_M.gguf new file mode 100644 index 0000000..85e7cf2 --- /dev/null +++ b/Qwen1.5-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2999028a7174bc3df6ab2f7bceb6cbeecbfb78aee4f9a390b3f5801298caf81 +size 2455116864 diff --git a/Qwen1.5-4B.Q4_K_S.gguf b/Qwen1.5-4B.Q4_K_S.gguf new file mode 100644 index 0000000..2a32232 --- /dev/null +++ b/Qwen1.5-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043221a8404307c2bee285618257a1c555956413ceef05efa829410e91d3c517 +size 2344422464 diff --git a/Qwen1.5-4B.Q5_K_M.gguf b/Qwen1.5-4B.Q5_K_M.gguf new file mode 100644 index 0000000..e806c39 --- /dev/null +++ b/Qwen1.5-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42694adae265f3548d401622778125de94a75e12c15d939cf02bc81f81c5834e +size 2839608384 diff --git a/Qwen1.5-4B.Q5_K_S.gguf b/Qwen1.5-4B.Q5_K_S.gguf new file mode 100644 index 0000000..c14016c --- /dev/null +++ b/Qwen1.5-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd4139623458fd027352d89d14fe05d3eb561ff20f0c79584f699a19bbe9a57 +size 2775198784 diff --git a/Qwen1.5-4B.Q6_K.gguf b/Qwen1.5-4B.Q6_K.gguf new file mode 100644 index 0000000..dad0ee5 --- /dev/null +++ b/Qwen1.5-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1566284c05f4d295fca5dadaf933572499d3d89982729adaefceab50c428f22d +size 3248130624 diff --git a/Qwen1.5-4B.Q8_0.gguf b/Qwen1.5-4B.Q8_0.gguf new file mode 100644 index 0000000..da566b7 --- /dev/null +++ b/Qwen1.5-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b0becc227a372468fe17fa3f236ec773ac1167bcb42b381a4626b0542ee5d4 +size 4204736064 diff --git a/Qwen1.5-4B.f16.gguf b/Qwen1.5-4B.f16.gguf new file mode 100644 index 0000000..6d350c4 --- /dev/null +++ b/Qwen1.5-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66a049f16c3cf43b79e3d3a90e566a63d0f5e915017d312c574e37895bdbead +size 7907724864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..367ee2d --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen1.5-4B +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-4B/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +tags: +- pretrained +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen1.5-4B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen1.5-4B-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/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.4 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-GGUF/resolve/main/Qwen1.5-4B.f16.gguf) | f16 | 8.0 | 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. + +