commit 0fd6fa8fe93fa6eca0661474d8802e76948b7819 Author: ModelHub XC Date: Thu May 28 12:56:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a48d82 --- /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 +Qwen3-VL-4B-Instruct-Unredacted-MAX.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf new file mode 100644 index 0000000..803cd3c --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431ad54d4e4b04dd883b05cceaca12c434894ae9cf38d0ba18b15306dc869ac8 +size 1127020032 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf new file mode 100644 index 0000000..f625085 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddad303ab7b14ace4aefb3aa8f4752e8d6e9f42b39625f7838dc1b25f1f9ed8 +size 1055258112 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf new file mode 100644 index 0000000..87c511a --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fef4bd124aa5fec52ec117ae50605dc4a182e0c83deb7b26c45367e4cddd2fa +size 1512986112 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf new file mode 100644 index 0000000..f0e970e --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1253af4cbf278c5d6ddb1a9ae6249f30758547814aebb94a6afe8b0d335ca7a +size 1417303552 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3c12b53 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca39135d545acd40e5f635503da0f94b1f8093e446f3962a60c0e431f833ae6 +size 1354102272 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0ed5c72 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c154b87ed1591d2aba59dc0a19248d9c74594fb02829146fd02feec13638d159 +size 1246623232 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf new file mode 100644 index 0000000..7cb1171 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2185de0f85e359c9eb9c9ef5cf0cefa761da0d65a227d131048dd8b9fbbd472e +size 1962898432 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf new file mode 100644 index 0000000..6f70532 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8b4a9f598c225e3c56aff4b9e653f76422c3eb97346c3e6430fde225a41e8f +size 1899533312 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5182c08 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a06e788ccbad899fed0a1e05189fc40f8728c0bc5bdcfaf8d83f4763a322875 +size 1814377472 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5b7edb2 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00930462385b582e38508272df07777bd42242cdc3bab25662ec6a646f6db0a +size 1670190592 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_NL.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5af563c --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a99f4cbd7af5c6220489ec5de9bcc8e7ccafa5149e18e8c49353c57d292cb4 +size 2381345792 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e83aeea --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be280a536aeb6be222d4fca2f4d887f5ff250dac95444c82e46a4e9235b8460b +size 2270753792 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K.gguf new file mode 100644 index 0000000..528eb15 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4914a63bb440ab07ca36ba1988aa402ac8f830dd2b7f02fc0454e1a8190baff8 +size 1669501952 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b6498eb --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1b2cb2a2e9f6d0b9ca237719a347ff45e93e409356c686b36c92f72382d6d1 +size 1563456512 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1966fdf --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d011cf267de71683dcda90c3239f9f12d130ecfaea1ea349130572b18d88ad9 +size 2239788032 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a062468 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f071ea9e72eaff688d5213e4899b6dc3d7eb4ee0fff107bf71352fad54c367 +size 2075620352 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3d59f2d --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b60a53a6c0ec537850be04899aca8ca43a328bb2f89675fbd1e3f88fe6084c3 +size 1886999552 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_0.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_0.gguf new file mode 100644 index 0000000..f675926 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1735b92e7822cffd0b337c94091b151f85238a604744aada1738f6bf30948782 +size 2375775232 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_1.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_1.gguf new file mode 100644 index 0000000..4c27ceb --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69b9afa24e284b576c19ed786d583735a2f2320853bd105604065c4f00be9fc +size 2596631552 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf new file mode 100644 index 0000000..1c48361 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c05fe931e24f948ab74fc21557d0f5a54cb4cb8a1870cbcad4b950a5c4d24d +size 2497283072 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a816ccb --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5385781741c8f506e2bee2917c286bdf58734bcb52d44eef8b517ef986b8e7 +size 2383311872 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf new file mode 100644 index 0000000..21d88ff --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c45c345767d364c8805104efe38416283acbaebb90e2ca3c679caf383ad692 +size 2889516032 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1243980 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6dc58c705894abf7b1666674d6c42cfebe98e20801285b8e7d0dfe51878d62b +size 2823713792 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q6_K.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q6_K.gguf new file mode 100644 index 0000000..0a2c729 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ea8953cdd1ab5394b03413187068fe50ade4055a5fb0c0727a24d71f4c80e1 +size 3306263552 diff --git a/Qwen3-VL-4B-Instruct-Unredacted-MAX.imatrix.gguf b/Qwen3-VL-4B-Instruct-Unredacted-MAX.imatrix.gguf new file mode 100644 index 0000000..2fb4f16 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-Unredacted-MAX.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e621725e74a476e667ddb079e77b1e6e19b562f86b2a19834b677099bd54ae +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..26c4fa5 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- uncensored +- abliterated +- unfiltered +- unredacted +- vllm +- pytorch +- bf16 +- max +- legal +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VL-4B-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/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-Unredacted-MAX.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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. + +