commit e293c1137743cdcf06539702d32adf60aab5ab71 Author: ModelHub XC Date: Mon Jul 20 04:23:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5840c5c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf new file mode 100644 index 0000000..39f88e4 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899096366fa4011152259a5b1b00bfa6a19d97c8c19722e1fcbddc9507dda7e0 +size 7932160128 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf new file mode 100644 index 0000000..e6071f9 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1450369d3ab37ba02bd07e31d77d37f70899d8ebdbae418c4ed5f784e45830 +size 7274506368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf new file mode 100644 index 0000000..d564428 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5be3b21cca8010ebf9c6c6c99d1312dc76faa6b5384a482be0512c9c1bffa54 +size 11264440448 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf new file mode 100644 index 0000000..5c743bc --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d8284945ee36eefa85865b4017d736990da4c571aaddb121f5fc755e853af1 +size 10387568768 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bbfc010 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39cadd6b41b374e39b3f0066cbf1920b34ec9a7283559066b7895cd1a78cd65f +size 9957550208 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ebcf0e0 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d609236d4ae984f886e70040541381d26be3f5b5ad30ddab9eef35115e1218 +size 9028249728 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf new file mode 100644 index 0000000..5358516 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7263fb8d90f6b51ac5d30d5468070dc4cc3481c7807e41b6bd0f494a5c6bd0aa +size 14810122368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf new file mode 100644 index 0000000..349695d --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b042d569bc64eb56f30cfe3f3810d3905e5522f3ddb118a0bfa3f53c5c9233 +size 14436894848 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf new file mode 100644 index 0000000..91ecec6 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da21ea660bfbd307ad1f94053e0510393b67a6e6abb7ae7a30f80d893223b6de +size 13705513088 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a595a82 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab713bb465e06cdc37590d32f874c52c6c33a17101d20b69aff75bee8f66b73d +size 12839270528 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf new file mode 100644 index 0000000..531105e --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607ba2aaef8a77d3ec67e5a86870f77d6be8a9ecda643d3ef158c1e9d1a1021f +size 17693153408 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K.gguf new file mode 100644 index 0000000..c019f29 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64962ef8056039782c4e566834c8615f68574a811bd0d13fc0b929473b0069de +size 12313098368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ad77ec2 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35344cb486168fbb03e161f23f86be990b99babc1dd6c411f82bffd42016890 +size 11488000128 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf new file mode 100644 index 0000000..202bc56 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a24a36d8507641a68e1a872af060283e302c70fadfd5a4051af870a43340ab +size 17247078528 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3d0dd0b --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9d9f7189cdd66b3870dd636d10c18520562393fb9283cb5a43b3213d689d3f +size 15935047808 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf new file mode 100644 index 0000000..cfa332a --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01133f6f1142710f8b1fd2d9ed1447cceac2d661a46e997e98c77023ca3e329 +size 14392330368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_0.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_0.gguf new file mode 100644 index 0000000..edf3399 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6ab0ce55cddf3ca42e666331c9945e0a844142877e53d6044ba4d12b8026bc +size 18711009408 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_1.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_1.gguf new file mode 100644 index 0000000..0295c0d --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c1c777b200d7e4961bf407d96a523bd612c4cb360eb458cd747c6ecc4c8340 +size 20639242368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf new file mode 100644 index 0000000..90e1d0b --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d08131894ae6e3da14a0140614f421e461fc26a04e3f54404204255200f4782 +size 19851335808 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b1968f5 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c71f45c40963c2c57dd34410d7f5a868e919d79e1e5e8b92e12571e5088ff0 +size 18784409728 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8a78f5d --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70d3afa18ef15c754abf4425c60e66dcad37ba8e65ec091c97ef6e41e65dc5b +size 23262156928 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6af79d6 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b8155141e76ffa14a1b450b5bc2bdb0bec78e0e2e7090b2681f29ab37d2448 +size 22638254208 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q6_K.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q6_K.gguf new file mode 100644 index 0000000..9ac6445 --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df7aded466c17a0e5a4c7c6a5d6fbb48d9a3e7deaf8983f376f7de3858d15ca +size 26886154368 diff --git a/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.imatrix.gguf b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.imatrix.gguf new file mode 100644 index 0000000..745abde --- /dev/null +++ b/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7f2525e4968a061106a177aa3080a213274d1196c7e5ca9fb55b358d1be7ca +size 15011072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9bbc24 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- BF16 +- text-generation-inference +- uncensored +- abliterated +- unfiltered +- unredacted +- vllm +- pytorch +- max +- legal +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-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-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen2.5-VL-32B-Instruct-Unredacted-MAX.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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. + +