commit 7ff7b0ed69bf97b8ab772af2f6c12d2ecb14e58e Author: ModelHub XC Date: Fri Jul 10 07:06:09 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0e0e32e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +QiMing-AD-20B-MXFP4.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-AD-20B-MXFP4.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QiMing-AD-20B-MXFP4.i1-IQ1_M.gguf b/QiMing-AD-20B-MXFP4.i1-IQ1_M.gguf new file mode 100644 index 0000000..3264c2d --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd08261fa9d4ddcffaa1fc9354ffdc0bdf9a7f627492502b679028d76e420074 +size 12016854592 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ1_S.gguf b/QiMing-AD-20B-MXFP4.i1-IQ1_S.gguf new file mode 100644 index 0000000..6c0303f --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dce14833ab44e48f48564cd7f3ba94ac61d5ae42a0a6ab7b1328a939019788a +size 12016854592 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ2_M.gguf b/QiMing-AD-20B-MXFP4.i1-IQ2_M.gguf new file mode 100644 index 0000000..fec7cc3 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61887a6096b18b009c8e794e9ef1ca1f040de385d60e95005edc9146ce7bd2e +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ2_S.gguf b/QiMing-AD-20B-MXFP4.i1-IQ2_S.gguf new file mode 100644 index 0000000..2f6b0ff --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c743080541d8f156b9600464fa5a4e00d112888cfed4dfbd3ab39139468ebf86 +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ2_XS.gguf b/QiMing-AD-20B-MXFP4.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2225d51 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b283fb51dee9d6ab0521f0dac662d288f92c6864a106328eefac4ac803cec1d +size 12025701952 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ2_XXS.gguf b/QiMing-AD-20B-MXFP4.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9ab821f --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf50950e82e636fe6ced927a556b513547e84e2e1ae245e60736bc589deb33a +size 12016854592 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ3_M.gguf b/QiMing-AD-20B-MXFP4.i1-IQ3_M.gguf new file mode 100644 index 0000000..f7ecefa --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9dfc7644c7139bce25ec33cfe178a7d3bc5fb6fd4eccdc6b0b15a08dae3a199 +size 12202649152 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ3_S.gguf b/QiMing-AD-20B-MXFP4.i1-IQ3_S.gguf new file mode 100644 index 0000000..cf99347 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931670b127a5bfde8e622ab69129fc1f579d10a97078d8d8831e497b46579f78 +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ3_XS.gguf b/QiMing-AD-20B-MXFP4.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cd02c9c --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac603b4ebb26d4c12772862e7773dd6784033bbdecf87b7babb50e756ec51f5 +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ3_XXS.gguf b/QiMing-AD-20B-MXFP4.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d566599 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f22b7b003f3a0a4030e47789c6ed2eecc9ed19992af8066980dc530b6dfe7f +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-IQ4_XS.gguf b/QiMing-AD-20B-MXFP4.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e2b32cf --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33219e027448a572972e99c88e78f3d5a37b1b7ba2d267ea819707a122667ae4 +size 12096480832 diff --git a/QiMing-AD-20B-MXFP4.i1-MXFP4_MOE.gguf b/QiMing-AD-20B-MXFP4.i1-MXFP4_MOE.gguf new file mode 100644 index 0000000..7d4782b --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-MXFP4_MOE.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fdf1a5015bcdd18b28de5601ce9579aadad6ed7de8a3aa139d37eb6dd1dd887 +size 12109567552 diff --git a/QiMing-AD-20B-MXFP4.i1-Q2_K.gguf b/QiMing-AD-20B-MXFP4.i1-Q2_K.gguf new file mode 100644 index 0000000..ce667ce --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb20cee9cc4d1b3ff2ab824ba21128c2a55f93e7e4e23375c3e91654c2c80c7 +size 12065515072 diff --git a/QiMing-AD-20B-MXFP4.i1-Q2_K_S.gguf b/QiMing-AD-20B-MXFP4.i1-Q2_K_S.gguf new file mode 100644 index 0000000..91d5c67 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c388a7c014369f0f255c5b5e1aef289ed4a0b1e19ee5aa453f3c08aadb860bac +size 12136293952 diff --git a/QiMing-AD-20B-MXFP4.i1-Q3_K_L.gguf b/QiMing-AD-20B-MXFP4.i1-Q3_K_L.gguf new file mode 100644 index 0000000..11bb841 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b9cf66f3fb0f79dbaef613d14592feee40c95dc92828e4ad5bf739dd49490e +size 13335111232 diff --git a/QiMing-AD-20B-MXFP4.i1-Q3_K_M.gguf b/QiMing-AD-20B-MXFP4.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f6011ea --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9663a35a7e6f9922d5580eeb6c56fa23930d4d5d11c6798d51d9e4b6caa43f +size 12916151872 diff --git a/QiMing-AD-20B-MXFP4.i1-Q3_K_S.gguf b/QiMing-AD-20B-MXFP4.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0b61afc --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4d2fb818b51d099bc066232c6ddf7ec85836f63a86def59469fa5d780cf96c +size 12061091392 diff --git a/QiMing-AD-20B-MXFP4.i1-Q4_0.gguf b/QiMing-AD-20B-MXFP4.i1-Q4_0.gguf new file mode 100644 index 0000000..3c34a6c --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d357412c5f88fc7e7fb2ed1fa75787aaddf3f8b414232e7bcd360f88c0b75cc3 +size 12148459072 diff --git a/QiMing-AD-20B-MXFP4.i1-Q4_1.gguf b/QiMing-AD-20B-MXFP4.i1-Q4_1.gguf new file mode 100644 index 0000000..4cd8cd3 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20010016c8660813adbb135bf0c89d2561fdc025a63c6c8f5db3607d2e2507b +size 13369095232 diff --git a/QiMing-AD-20B-MXFP4.i1-Q4_K_M.gguf b/QiMing-AD-20B-MXFP4.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5cddd3c --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c981668799e28106ca519159c1bc8875712949aafc44f43d4a5de980b52c3c42 +size 15805137472 diff --git a/QiMing-AD-20B-MXFP4.i1-Q4_K_S.gguf b/QiMing-AD-20B-MXFP4.i1-Q4_K_S.gguf new file mode 100644 index 0000000..122d4c7 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e279982ffcfe04f8d81322ef528f98b0a4ac42184ea29cb3dc5984a2f91f64 +size 14654243392 diff --git a/QiMing-AD-20B-MXFP4.i1-Q5_K_M.gguf b/QiMing-AD-20B-MXFP4.i1-Q5_K_M.gguf new file mode 100644 index 0000000..29f7d9d --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b601c7a39a0cc3a5ebe3c26dbdf049c1309775edc6590bd13014f072c20396 +size 16893063232 diff --git a/QiMing-AD-20B-MXFP4.i1-Q5_K_S.gguf b/QiMing-AD-20B-MXFP4.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fb2c978 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a358fd0eb8c09ee757942ddbfd72d4a854dd05c259a7ea6cc13f62e1e27a14a6 +size 15892205632 diff --git a/QiMing-AD-20B-MXFP4.i1-Q6_K.gguf b/QiMing-AD-20B-MXFP4.i1-Q6_K.gguf new file mode 100644 index 0000000..53eeb62 --- /dev/null +++ b/QiMing-AD-20B-MXFP4.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c085ad4062fa229f5c346d865a1ab40bc8d5aa166cfa495d6feac8aaf43115 +size 22193346112 diff --git a/QiMing-AD-20B-MXFP4.imatrix.gguf b/QiMing-AD-20B-MXFP4.imatrix.gguf new file mode 100644 index 0000000..d264f5f --- /dev/null +++ b/QiMing-AD-20B-MXFP4.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878123e14139850063651f6d699ea4e4e790365a6d039b6d40bff9b0e6d61954 +size 28079776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e258094 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: aifeifei798/QiMing-AD-20B-MXFP4 +language: +- en +- zh +library_name: transformers +license: apache-2.0 +model_name: QiMing-AD-20B-MXFP4 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- QiMing +- vllm +- sales +- b2b +- Strategist +- saas +- fine-tuned +- instruction-following +- role-playing +- cognitive-simulator +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/aifeifei798/QiMing-AD-20B-MXFP4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QiMing-AD-20B-MXFP4-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-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/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-AD-20B-MXFP4-i1-GGUF/resolve/main/QiMing-AD-20B-MXFP4.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +