commit 88f9762874ebf56b4b0a1d17db62d45871fdf8ad Author: ModelHub XC Date: Thu Jun 4 21:09:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/QAi-1.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..06307a4 --- /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 +QAi-1.1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAi-1.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QAi-1.1.i1-IQ1_M.gguf b/QAi-1.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..29fd6f9 --- /dev/null +++ b/QAi-1.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9dce89d99f19080742124c34eb79353f91fa30993dd3ea20f00401cf6247af +size 850028032 diff --git a/QAi-1.1.i1-IQ1_S.gguf b/QAi-1.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..b906357 --- /dev/null +++ b/QAi-1.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281f57c6c38a041eb246d5506e908421983e2b106e4e502ae21ccd6fb849c63a +size 791094784 diff --git a/QAi-1.1.i1-IQ2_M.gguf b/QAi-1.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..0d48925 --- /dev/null +++ b/QAi-1.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b84e679fbbb1331e3ae181af99bcda23a4561b19f3c1e124c93cf655a7f9312 +size 1140516352 diff --git a/QAi-1.1.i1-IQ2_S.gguf b/QAi-1.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..3acf178 --- /dev/null +++ b/QAi-1.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9089053ae0dfc75f0b30f23fb8db3e57b43c43f45d443adb6f561c4c9df41a4c +size 1061938688 diff --git a/QAi-1.1.i1-IQ2_XS.gguf b/QAi-1.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a77531b --- /dev/null +++ b/QAi-1.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb168d08183302e60aa7af56b7e66974593247d7bada5a2b6b7742b3688e6ec +size 1031546368 diff --git a/QAi-1.1.i1-IQ2_XXS.gguf b/QAi-1.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b78ccfc --- /dev/null +++ b/QAi-1.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06932bcab8f2aba2787e7095340590a29666805da3fe064cb8c33c656d820e14 +size 948250112 diff --git a/QAi-1.1.i1-IQ3_M.gguf b/QAi-1.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..e88010c --- /dev/null +++ b/QAi-1.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2da0b7a3344aeab97d612b89a61c93461a28f8f7182e47478ec0a5d41b73c09 +size 1488895488 diff --git a/QAi-1.1.i1-IQ3_S.gguf b/QAi-1.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..31b064f --- /dev/null +++ b/QAi-1.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73715deccf7847ec02003cbd02dc5324a6a1f92df3dcee8240c2e27f183345b +size 1456864768 diff --git a/QAi-1.1.i1-IQ3_XS.gguf b/QAi-1.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..93fd2ad --- /dev/null +++ b/QAi-1.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25c5df29743bf58fbd981b5c60c5f1e047099027bb6154fe44ee24ae1e5f6e2 +size 1391836672 diff --git a/QAi-1.1.i1-IQ3_XXS.gguf b/QAi-1.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5a715d7 --- /dev/null +++ b/QAi-1.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2debc0c29bb5b29abf35d69b765ed1ee8afb65ed203ab0f85fe10e29f6f14f7 +size 1282827776 diff --git a/QAi-1.1.i1-IQ4_NL.gguf b/QAi-1.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cf74a38 --- /dev/null +++ b/QAi-1.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e24ef8dcfe35620063b637723f3f4828428f270425d57589ebc66e89a6d8f3 +size 1825209856 diff --git a/QAi-1.1.i1-IQ4_XS.gguf b/QAi-1.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9372c21 --- /dev/null +++ b/QAi-1.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:addf91607224c68ec6c27c50825f2efd12fabf47ee95fc03220857a0a1ea7137 +size 1739095552 diff --git a/QAi-1.1.i1-Q2_K.gguf b/QAi-1.1.i1-Q2_K.gguf new file mode 100644 index 0000000..a8ca875 --- /dev/null +++ b/QAi-1.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aaf220836495ffcfe15779e1536ca3fcfc940af5bb6cda93aea1ae87e1465bf +size 1274756608 diff --git a/QAi-1.1.i1-Q2_K_S.gguf b/QAi-1.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e40c623 --- /dev/null +++ b/QAi-1.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccaf0243ad825a3bc49d65cee6663adac5b5a56aabf16bca051ac947f580bf4 +size 1198128640 diff --git a/QAi-1.1.i1-Q3_K_L.gguf b/QAi-1.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8af2ca9 --- /dev/null +++ b/QAi-1.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e2dedf8c4434d03beb00c039c6bba9dce2910176803a4add020c1734243cc4 +size 1707392512 diff --git a/QAi-1.1.i1-Q3_K_M.gguf b/QAi-1.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..51df2d3 --- /dev/null +++ b/QAi-1.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38421f76e9982131ff88410b1252652a174bdf8e47909092f70c5f38ac34de35 +size 1590476288 diff --git a/QAi-1.1.i1-Q3_K_S.gguf b/QAi-1.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8687a6b --- /dev/null +++ b/QAi-1.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eda22ce7d9ee19db6543aee1d7abbaf192c80958e8a3b5513d53b725ec1dd7 +size 1454358016 diff --git a/QAi-1.1.i1-Q4_0.gguf b/QAi-1.1.i1-Q4_0.gguf new file mode 100644 index 0000000..a83ae3e --- /dev/null +++ b/QAi-1.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58915eb126c098e8bc15555fa18f28ea90412d1cf6e0b784e6e4a03a8eebb808 +size 1828486656 diff --git a/QAi-1.1.i1-Q4_1.gguf b/QAi-1.1.i1-Q4_1.gguf new file mode 100644 index 0000000..615106a --- /dev/null +++ b/QAi-1.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86de5282ffc9783c13a688b635316c347739d28649c6c1d86a7bd826dfe62b3 +size 1996258816 diff --git a/QAi-1.1.i1-Q4_K_M.gguf b/QAi-1.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..eda17f3 --- /dev/null +++ b/QAi-1.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:673bd30957762fe1d44001b669d73c8b1331344b283a4cdae72990ea9cfa23fc +size 1929903616 diff --git a/QAi-1.1.i1-Q4_K_S.gguf b/QAi-1.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1d8e0d3 --- /dev/null +++ b/QAi-1.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81e3fb446f921f5cc9aa82268da738c4f6dd55c63693ab72b2d13ce3c092fdc +size 1834384896 diff --git a/QAi-1.1.i1-Q5_K_M.gguf b/QAi-1.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a4ba1c4 --- /dev/null +++ b/QAi-1.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccaea5ed05c30b7fccbe609f83b6353bba7037b87b1f7fb003fec64548bc4150 +size 2224815616 diff --git a/QAi-1.1.i1-Q5_K_S.gguf b/QAi-1.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..36a8d63 --- /dev/null +++ b/QAi-1.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7e783adfb47174797c98e95ea3cec8f602b828844df4be79cd39e6e0c9acf4 +size 2169667072 diff --git a/QAi-1.1.i1-Q6_K.gguf b/QAi-1.1.i1-Q6_K.gguf new file mode 100644 index 0000000..d0debb6 --- /dev/null +++ b/QAi-1.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e00deeedb8992d7fd8ee1636013fd8f4c982e3bf26d53cc35102b60c5b5770 +size 2538159616 diff --git a/QAi-1.1.imatrix.gguf b/QAi-1.1.imatrix.gguf new file mode 100644 index 0000000..bc47263 --- /dev/null +++ b/QAi-1.1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d928102867e5683a9b747ffedd24aa5f291ae6dd6249b6919113cfcb2f2842f +size 3393408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..898e77b --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: QwexGP/QAi-1.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/QwexGP/QAi-1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QAi-1.1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/QAi-1.1-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/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QAi-1.1-i1-GGUF/resolve/main/QAi-1.1.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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. + +