commit 1babb43edb984f83e6efa1d245fd96939a94ac10 Author: ModelHub XC Date: Mon Apr 20 16:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2eee0f1 --- /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-Thinking-Unredacted-MAX.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_M.gguf new file mode 100644 index 0000000..c8821f7 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd8419bf5fb199d1cf56d20b1acf8cc7c334485f81d498edc0327684bf8ff34 +size 1127019904 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_S.gguf new file mode 100644 index 0000000..03b8d19 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef932c0a9b17936c79f480bb6f2ecbd0203d5a2d227d2ead2069b14804f14ea3 +size 1055257984 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_M.gguf new file mode 100644 index 0000000..cfe367c --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369ca9d63dc9da347e2fde2310fcb150b4910f88b443573ca7734e667fa8d108 +size 1512985984 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_S.gguf new file mode 100644 index 0000000..2e58441 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265a3f94d82bca269ce04c0011192dc1d5c5c4721679b3780a5993046b386b57 +size 1417303424 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XS.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XS.gguf new file mode 100644 index 0000000..03f07db --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edb14da7150096fa4b121b0d5c090a32d0906c6906b1ec8f218a4fe0daff266 +size 1354102144 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XXS.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c15fb69 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70500beb67145d4724927cb8a8554cf8f13e2b6247e79755f16533b65413ff42 +size 1246623104 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_M.gguf new file mode 100644 index 0000000..727f3c6 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33da24c854e7364ab6eb3ad3370c60ca14bb3815559c1879d926f2b83dac84e9 +size 1962898304 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_S.gguf new file mode 100644 index 0000000..8b35864 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e62e6ecb5342076d504fba457225acf61d65e68ba845c69cd6c9fcc5583d3ad +size 1899533184 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XS.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e662e58 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d66ed881632106677421dce9e0c0df9f82eff07993d4f8bfbd44371be206abb +size 1814377344 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XXS.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..de2fe24 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b99bb97c78f9fb0938eefa8e87c7dec02a66d4c86974096f6167a3bb3fb395 +size 1670190464 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_NL.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_NL.gguf new file mode 100644 index 0000000..03cb6bc --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6077f43e182e2c7f4e5f21ac98fe0c831c57fc384b8cdafb278aa74a2faacc +size 2381345664 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_XS.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_XS.gguf new file mode 100644 index 0000000..788a16c --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7946d0f409989d52bfea94528ebbec0d8b1b44df4fac21cc67526f094d02f25a +size 2270753664 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K.gguf new file mode 100644 index 0000000..b0f5b3c --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ebe7093a65c52aaea9530a8367cf2959897b4d7475bf04ca33f87363d29147 +size 1669501824 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K_S.gguf new file mode 100644 index 0000000..976fdf6 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99e84a0db3723cd722bb9b5aa563aed83f29301a38fb3ebf193cbc69672450d +size 1563456384 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_L.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8d6b74e --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c2ef09fe4135a724fc4805626686e1f03e1a21969b6a270e497d3d9d655fe5 +size 2239787904 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1ce643c --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4108c94c018ad05c47fc426608b79afc9e402ce931e6704d9a2042be168f5f87 +size 2075620224 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_S.gguf new file mode 100644 index 0000000..28972ce --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea36fda92f588caabbaba047a9f34e38effb933618de07e19a6fdf5afb1379f +size 1886999424 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_0.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_0.gguf new file mode 100644 index 0000000..c704e61 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2753ef7e78918375aaa199a5384ea7a89dca1db6015b16df210b388e981baf3 +size 2375775104 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_1.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_1.gguf new file mode 100644 index 0000000..8e46114 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9c111f6deb443d8fc7dff189559ee10cd1706a8e3110c0ebf5a3f0f4a2efa0 +size 2596631424 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_M.gguf new file mode 100644 index 0000000..cf08e65 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0437f551e42d1afd8e6d329f3c9b497ed4be9ed121dc38ce951b213ff675c9 +size 2497282944 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0ec7f9c --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83cea1df932ca110e320afc4cdae1959d8af23b1490f23384f987be695e68a6 +size 2383311744 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_M.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c1ec1ae --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0364f3b44715727f883d107f5a57ec3d4d0357c5d456043c2ad6d2ae35a9d30f +size 2889515904 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_S.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8f1efeb --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106f7d1217ad8b760f3e15953f7a1c8e56e08fbe9f6aa5e7727064b6d242bf74 +size 2823713664 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q6_K.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q6_K.gguf new file mode 100644 index 0000000..948ca96 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54812e3f3995acaa68a525419bf73c87f0284f5a89598f6f28045d1cd6dc04d6 +size 3306263424 diff --git a/Qwen3-VL-4B-Thinking-Unredacted-MAX.imatrix.gguf b/Qwen3-VL-4B-Thinking-Unredacted-MAX.imatrix.gguf new file mode 100644 index 0000000..ba8c100 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-Unredacted-MAX.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bce0a2391cb60dd23a0d67577e7396829b1b4864f223b1e0594a97ef8614970 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59185bc --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: prithivMLmods/Qwen3-VL-4B-Thinking-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 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-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-Thinking-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-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-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-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-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-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-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-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-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-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-Unredacted-MAX.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-Unredacted-MAX-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-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. + +