commit 339bdda15ddc831af8caa618910a1f19686e662e Author: ModelHub XC Date: Mon Oct 5 08:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3736bc --- /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 +R3-Qwen2.5-7B-4k.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen2.5-7B-4k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R3-Qwen2.5-7B-4k.i1-IQ1_M.gguf b/R3-Qwen2.5-7B-4k.i1-IQ1_M.gguf new file mode 100644 index 0000000..acab19d --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e279e053473fb0d5405c79b023f413b7c5b3b2efea57bd39b07b0190c4878d59 +size 2042196576 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ1_S.gguf b/R3-Qwen2.5-7B-4k.i1-IQ1_S.gguf new file mode 100644 index 0000000..7457e32 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dfda8f7dde5af3949784b18154a2411073408f7008d7f0355c7203753b6dce +size 1903667808 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ2_M.gguf b/R3-Qwen2.5-7B-4k.i1-IQ2_M.gguf new file mode 100644 index 0000000..72934ee --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7693085a27d2360cf28d4ddda12a09469ce2f58b25b27c9eef05f7701e7fb5 +size 2780342880 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ2_S.gguf b/R3-Qwen2.5-7B-4k.i1-IQ2_S.gguf new file mode 100644 index 0000000..63f79cc --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b999efc9ef72a711efac69a3f4c6fd4eda4d0c6d71292ba509b05cacda890a +size 2595637856 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ2_XS.gguf b/R3-Qwen2.5-7B-4k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3e14f65 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14053639ea08aee892b75af2fc5459f747f7e63e26e99bfd0a6d89cbc447a461 +size 2469022304 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ2_XXS.gguf b/R3-Qwen2.5-7B-4k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1c0ea4b --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5dd7bdedfbdf91cafe7f739f3bed88b11155724c00e80b7416855c165fad50a +size 2273077856 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ3_M.gguf b/R3-Qwen2.5-7B-4k.i1-IQ3_M.gguf new file mode 100644 index 0000000..438b9b6 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5ecc8fc00d12f449d38856a6bd89e52ec73f8a61f17a022153ccfe626d76c8 +size 3574012512 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ3_S.gguf b/R3-Qwen2.5-7B-4k.i1-IQ3_S.gguf new file mode 100644 index 0000000..8b17f3c --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:577cf395da590a39ddbdc42cb5ec1b7b9e3f48ec167a61601a78be721ba034e9 +size 3499192928 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ3_XS.gguf b/R3-Qwen2.5-7B-4k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4060dfc --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9022cfb482ca9643bfaf646d61000045feca259e42ca46c88aa4aece3b358739 +size 3346256480 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ3_XXS.gguf b/R3-Qwen2.5-7B-4k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..32a9e60 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7394924d971b23dbf6e79c3e904c9776046af39bbe87a301399e038d74905cc +size 3114515040 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ4_NL.gguf b/R3-Qwen2.5-7B-4k.i1-IQ4_NL.gguf new file mode 100644 index 0000000..63245ad --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8df3e9cae5867bb576c8b367bc81ebd4abfb875bff6184142f3ca3f140f91a0 +size 4437813856 diff --git a/R3-Qwen2.5-7B-4k.i1-IQ4_XS.gguf b/R3-Qwen2.5-7B-4k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..defa447 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a86e129720506690c9516f39b978564d66891be145f1e8e7a4ae68669bb0fd +size 4218473056 diff --git a/R3-Qwen2.5-7B-4k.i1-Q2_K.gguf b/R3-Qwen2.5-7B-4k.i1-Q2_K.gguf new file mode 100644 index 0000000..9418807 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58af84466a4cbb2f5b05936a63a24975327dd494d34ee0da1cf6bb5bd1aac8dd +size 3015940704 diff --git a/R3-Qwen2.5-7B-4k.i1-Q2_K_S.gguf b/R3-Qwen2.5-7B-4k.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7168bf0 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ea006e0ef753fe4c9adc7ae426fc61dd40b64895a6739b50b6bc89de8bc052 +size 2834074208 diff --git a/R3-Qwen2.5-7B-4k.i1-Q3_K_L.gguf b/R3-Qwen2.5-7B-4k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d74c434 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c3190fd49516dad95fe2dd6b533149fa1feff2c5f232da9fab34e3a0322ed0 +size 4088459872 diff --git a/R3-Qwen2.5-7B-4k.i1-Q3_K_M.gguf b/R3-Qwen2.5-7B-4k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b8941c9 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c02b5fb8ad59171c493bf2f50cd7ae86a5f4e5776d61e59265beaf6bdc8b440 +size 3808391776 diff --git a/R3-Qwen2.5-7B-4k.i1-Q3_K_S.gguf b/R3-Qwen2.5-7B-4k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..fedfd9e --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b52368be692dc944ea35d68d7104032cbc8f32ec7a6b1097e8795ade8a075f6 +size 3492368992 diff --git a/R3-Qwen2.5-7B-4k.i1-Q4_0.gguf b/R3-Qwen2.5-7B-4k.i1-Q4_0.gguf new file mode 100644 index 0000000..50bbf85 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0103e59d3416ae58eb04427d7c65794ecbb44edb7193f59a973082b44dd90c7 +size 4444121696 diff --git a/R3-Qwen2.5-7B-4k.i1-Q4_1.gguf b/R3-Qwen2.5-7B-4k.i1-Q4_1.gguf new file mode 100644 index 0000000..3b6cba8 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc10b7faeae3836cfde25b90041e53c26acd7e65c34fdb6a3dc8a16b6585fa24 +size 4873284192 diff --git a/R3-Qwen2.5-7B-4k.i1-Q4_K_M.gguf b/R3-Qwen2.5-7B-4k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b061c7b --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cafe92bbd76f1644e7e7fcb69de124b7c261886a3e79f41cd7a7344b8aefba +size 4683074144 diff --git a/R3-Qwen2.5-7B-4k.i1-Q4_K_S.gguf b/R3-Qwen2.5-7B-4k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..45d6007 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453c95aff18725aeb1798657c8f429879a54a6ed920a305f6d31b088d007ab94 +size 4457769568 diff --git a/R3-Qwen2.5-7B-4k.i1-Q5_K_M.gguf b/R3-Qwen2.5-7B-4k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b82ba8f --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ce21edab97532b48ec6eebecfed96a35d03071ece31a588242d8f9f9e2c774 +size 5444831840 diff --git a/R3-Qwen2.5-7B-4k.i1-Q5_K_S.gguf b/R3-Qwen2.5-7B-4k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..faaa0b5 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85728dceae9efd96df72d202edfaa7437434b8d5f6093be2dc2d5b4cad0d15dd +size 5315177056 diff --git a/R3-Qwen2.5-7B-4k.i1-Q6_K.gguf b/R3-Qwen2.5-7B-4k.i1-Q6_K.gguf new file mode 100644 index 0000000..4cb8d51 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e210b8e46a2690897339c89a00aa0b450734d6e83460aac1b2c6e800e26349 +size 6254199392 diff --git a/R3-Qwen2.5-7B-4k.imatrix.gguf b/R3-Qwen2.5-7B-4k.imatrix.gguf new file mode 100644 index 0000000..0ed4860 --- /dev/null +++ b/R3-Qwen2.5-7B-4k.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec56ff76df298481a3bdd08d7fbc3dacf2a25f51c58c382879e98f98edeeb479 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6945fa --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: rubricreward/R3-Qwen2.5-7B-4k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/rubricreward/R3-Qwen2.5-7B-4k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#R3-Qwen2.5-7B-4k-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-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/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen2.5-7B-4k-i1-GGUF/resolve/main/R3-Qwen2.5-7B-4k.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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. + +