commit aafbbd0114ec9e8885578fe5b9b15299f7e073ea Author: ModelHub XC Date: Thu Apr 30 18:50:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a673a16 --- /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-2B-Thinking.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Thinking.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-2B-Thinking.i1-IQ1_M.gguf b/Qwen3-VL-2B-Thinking.i1-IQ1_M.gguf new file mode 100644 index 0000000..ee2ee11 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91578a92deb62450936e7a604b3807568911ec30998d71d78702d2f6578040dd +size 543794848 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ1_S.gguf b/Qwen3-VL-2B-Thinking.i1-IQ1_S.gguf new file mode 100644 index 0000000..27d95fc --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90695ee602b765f3121ab3931e735852016e170dec0468a28e7aaccac06190c6 +size 515778208 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ2_M.gguf b/Qwen3-VL-2B-Thinking.i1-IQ2_M.gguf new file mode 100644 index 0000000..189e045 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cbe44e5aab233655bbadc8d09a9581096af87efd7d57da463bdde13e6d85251 +size 695183008 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ2_S.gguf b/Qwen3-VL-2B-Thinking.i1-IQ2_S.gguf new file mode 100644 index 0000000..093fa6b --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d23478b280501796ff564d69044922f731f852fcc896399116317c050539b1e +size 657827488 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ2_XS.gguf b/Qwen3-VL-2B-Thinking.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4e3cc8d --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde3f77e5df12f866594def67353ff19cb66c38ab03552ef650b3a268544c8fa +size 631514784 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ2_XXS.gguf b/Qwen3-VL-2B-Thinking.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3305431 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ecad852be3abf52aaae8b41244f8761ab2e91c2b8df4b08377c81dfe2d66aa +size 590489248 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ3_M.gguf b/Qwen3-VL-2B-Thinking.i1-IQ3_M.gguf new file mode 100644 index 0000000..efb7f97 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db28d6be4cf245f250ffc27dc5b00d17aa37d33dc49374aeed324cced529768 +size 895663776 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ3_S.gguf b/Qwen3-VL-2B-Thinking.i1-IQ3_S.gguf new file mode 100644 index 0000000..4bfbef1 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56513338d0b3a7e8d80dda102223dd0ff46bcce0334ef98d2c1d09d18276b63d +size 867253920 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ3_XS.gguf b/Qwen3-VL-2B-Thinking.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e06d457 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d10ed6e3111cb290e9f28cfc5c8c31932d5d6094b75bc14fe2e77a4fd80400c +size 834223776 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ3_XXS.gguf b/Qwen3-VL-2B-Thinking.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d05bf83 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0ea8a07e5bce51811cff651750524ddcc5ada833cb9b5fff1621c7ff6640e0 +size 754362016 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ4_NL.gguf b/Qwen3-VL-2B-Thinking.i1-IQ4_NL.gguf new file mode 100644 index 0000000..78b0cd6 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab06ef0e57b0d9755d1c6538aeddf413fe74f5908686a17d22d2d7556dc067a3 +size 1054424736 diff --git a/Qwen3-VL-2B-Thinking.i1-IQ4_XS.gguf b/Qwen3-VL-2B-Thinking.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9de4174 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ace8985a5a1969b2824ff63edcd2a33fc0e80a7e3f3e8f2f6f56c9b0160c90 +size 1010384544 diff --git a/Qwen3-VL-2B-Thinking.i1-Q2_K.gguf b/Qwen3-VL-2B-Thinking.i1-Q2_K.gguf new file mode 100644 index 0000000..0cb56d2 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b97d3800e59e6ff2eef0eb9965e2ce0f4c9e87cfaa081ea1cbbb650e6e74f0 +size 777797280 diff --git a/Qwen3-VL-2B-Thinking.i1-Q2_K_S.gguf b/Qwen3-VL-2B-Thinking.i1-Q2_K_S.gguf new file mode 100644 index 0000000..18274d6 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f39955b16f4f023907d53e3ed8186f5634b8f15a52922049a94f88a53ee13a +size 732970656 diff --git a/Qwen3-VL-2B-Thinking.i1-Q3_K_L.gguf b/Qwen3-VL-2B-Thinking.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ef27d38 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b27c2960698379950e4013c934b530877d1c49732282bd56f2ba89cd66c8547e +size 1003503264 diff --git a/Qwen3-VL-2B-Thinking.i1-Q3_K_M.gguf b/Qwen3-VL-2B-Thinking.i1-Q3_K_M.gguf new file mode 100644 index 0000000..195e367 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da2a7255b8ca58598cdf8b45a0ba946ebb6484d6173d1af2283f1e46a522e78 +size 939540128 diff --git a/Qwen3-VL-2B-Thinking.i1-Q3_K_S.gguf b/Qwen3-VL-2B-Thinking.i1-Q3_K_S.gguf new file mode 100644 index 0000000..213858a --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6daf8e2d53e64aee86d57cba99f2fa2e572a10f7523217ad6a3b185de32ad6d9 +size 867253920 diff --git a/Qwen3-VL-2B-Thinking.i1-Q4_0.gguf b/Qwen3-VL-2B-Thinking.i1-Q4_0.gguf new file mode 100644 index 0000000..95b16a1 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64151b0fd75555a648eed71b4a5fff5f0e4f6b4568d54a2ea01b186fd6554c16 +size 1056784032 diff --git a/Qwen3-VL-2B-Thinking.i1-Q4_1.gguf b/Qwen3-VL-2B-Thinking.i1-Q4_1.gguf new file mode 100644 index 0000000..0dd1782 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9c27d187ca5975753fd59bfa79e425a9a998fd9572b24b2192689c323f471e +size 1142505120 diff --git a/Qwen3-VL-2B-Thinking.i1-Q4_K_M.gguf b/Qwen3-VL-2B-Thinking.i1-Q4_K_M.gguf new file mode 100644 index 0000000..103c6cd --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70df73075d7b84be5f55fdf04cf2e3ffea0babdefc7a998568a1c7e55ddd0e4 +size 1107410592 diff --git a/Qwen3-VL-2B-Thinking.i1-Q4_K_S.gguf b/Qwen3-VL-2B-Thinking.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7e7639b --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35062b5accbdaac709f72364826e8c109154e4ae421789f3196313bab38ccf92 +size 1060191904 diff --git a/Qwen3-VL-2B-Thinking.i1-Q5_K_M.gguf b/Qwen3-VL-2B-Thinking.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c5f9d36 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1d7173aa86eecda720aeeb8e6fc79bd9e97f07045245bcf02f3093381acecb +size 1257881248 diff --git a/Qwen3-VL-2B-Thinking.i1-Q5_K_S.gguf b/Qwen3-VL-2B-Thinking.i1-Q5_K_S.gguf new file mode 100644 index 0000000..918c3cf --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e42fd056af287b7d4421e5644bedae00f4c12fbfd9a6baec15e597c3f139dd +size 1230585504 diff --git a/Qwen3-VL-2B-Thinking.i1-Q6_K.gguf b/Qwen3-VL-2B-Thinking.i1-Q6_K.gguf new file mode 100644 index 0000000..7e1ff86 --- /dev/null +++ b/Qwen3-VL-2B-Thinking.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e89a514620a961b535b34b1392a0f5651bd303388b0624176f5b612a600164 +size 1417756320 diff --git a/Qwen3-VL-2B-Thinking.imatrix.gguf b/Qwen3-VL-2B-Thinking.imatrix.gguf new file mode 100644 index 0000000..d14711d --- /dev/null +++ b/Qwen3-VL-2B-Thinking.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9c2169fb130c01db9a2f49328c125ea7ad766f0d1b3fd2fac1bdbefd5730ec +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7029a5d --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: Qwen/Qwen3-VL-2B-Thinking +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-VL-2B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-2B-Thinking-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-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-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF/resolve/main/Qwen3-VL-2B-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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. + +