commit 415e9cbfd6a42a2bbc4c3e3aec727641a442700c Author: ModelHub XC Date: Tue Apr 21 21:07:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bc2decc --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-R2R-low-level.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_M.gguf new file mode 100644 index 0000000..d7c1c0e --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9b34e46fbd654daaf368806f5798ff3ba2d527d56fe77cbaab66b8d16a3a1e +size 850026656 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_S.gguf new file mode 100644 index 0000000..e4049ad --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64383ff7dafed9ae0d6218d751fb523beae8b058bdfe94cfd80851f7640ff225 +size 791093408 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_M.gguf new file mode 100644 index 0000000..46e7d1e --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51505afefc3fe132eb9f70593e95d5ba935b7bedeae73ec95389ebe3d22fc86c +size 1140514976 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_S.gguf new file mode 100644 index 0000000..b2fbd8d --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ffa4b030a61b6fb2dbb5cb683c2703715bf662ad39da9f7dfc10d7b075c3713 +size 1061937312 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XS.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fa8c6fd --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a12ce88f2183cdb22f7bd95f63cf143203be3bedeaa61ab9b1908fa74385d58 +size 1031544992 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XXS.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5ae0f6f --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48659b01f8086de8c245639189abda831abc14f19d10cc15994efa075adfc3e +size 948248736 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_M.gguf new file mode 100644 index 0000000..7d7d7a1 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d064b4b14dc0dd643b71fe8ec841dfd2151b521befda0e47e9a37ae985251a +size 1488894112 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_S.gguf new file mode 100644 index 0000000..a01d1f2 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a2fbd788b51ecd80bf825803c29e3fa89dd989841bfbd6944030072fcd3197 +size 1456863392 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XS.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ec74b04 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65513adb2ef02172b6ffd33ed0af0ca67227d50cace54c093c4f2b73c4a35b1d +size 1391835296 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XXS.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..29531e8 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56acc13b8805b0a348c4c4dbd0ed18d71cc71351fee71466784599845720710a +size 1282826400 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_NL.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2f71d9b --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f0e7fb0811489a81e4a5551f652abbfa3c6ebeb2fe99aa4f810bfbacdad641 +size 1825208480 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_XS.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_XS.gguf new file mode 100644 index 0000000..50fa0dc --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9faa0a52b1a7f8526fde7d3cfb27817d2d4ec6746f690334991d4112c1fb0a9 +size 1739094176 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K.gguf new file mode 100644 index 0000000..6933dbe --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a5b60dbf9e207f375a72994e1033188a2b84656f8316c5dbce870a412d88ae +size 1274755232 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f2bab67 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fcb59521cbfbf6dab5719bfe891a0056103e54ecf8fa4bfaf30508b53a1f948 +size 1198127264 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_L.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_L.gguf new file mode 100644 index 0000000..00b9e74 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f82aacb19b7f9d7769f70627cea0d77e9f38bc6b90a058b96fb0b6c6c2dd56 +size 1707391136 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a2cddb4 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fca4223337183fea50d7b05da26cee4416cd924170886e89e81d2bc23e4029d +size 1590474912 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e4fafcc --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8224510665f42ddb430929484a237067f2bed39536c57516e4a79ab138fdb3 +size 1454356640 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_0.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_0.gguf new file mode 100644 index 0000000..e324a94 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b881531ac76aa75418516b790b468928de50156ecd4016efce58cd0c0eaca28 +size 1828485280 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_1.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_1.gguf new file mode 100644 index 0000000..996eec0 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebf62ea70c0a5ef5fe278d68bf8055fe07767f5ba1d61d74c2d530a5a50b34e +size 1996257440 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6a879ce --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9346d70d6e93d0d4d110b36b4edef28fd7c8722a2333319a80c9683c6cf179 +size 1929902240 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d755678 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5803552b5bfbf33cebee285d9cef787eb48a91eefe78315a8b847d758ed5ae4 +size 1834383520 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_M.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_M.gguf new file mode 100644 index 0000000..65a3793 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31aa6c52cd7847b8e0f3715782153d73113c15f352f1ca297cfc2595735abb64 +size 2224814240 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_S.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2330915 --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48acf04efe8efbdf3f418aff9644f08ea7a653a2176cf3ac17de81a9cf22e70e +size 2169665696 diff --git a/Qwen2.5-VL-3B-R2R-low-level.i1-Q6_K.gguf b/Qwen2.5-VL-3B-R2R-low-level.i1-Q6_K.gguf new file mode 100644 index 0000000..0eb84ed --- /dev/null +++ b/Qwen2.5-VL-3B-R2R-low-level.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af61a863462ec500c3a60d9b40774669de56e054cb0db92826702d6003a6b185 +size 2538158240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad7427d --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: Vebbern/Qwen2.5-VL-3B-R2R-low-level +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Room-to-Room +- R2R +- VLN +- Vision-and-Language-Navigation +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Vebbern/Qwen2.5-VL-3B-R2R-low-level + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-3B-R2R-low-level-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-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/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF/resolve/main/Qwen2.5-VL-3B-R2R-low-level.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..8787bc0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3866c1ca562edd1e1110539d02d66e69399c1fe8e85b039ee344df3d392a48e +size 3362977