commit a072cea25299c3bbaabc6a804e872a64ddae6826 Author: ModelHub XC Date: Sun Apr 12 14:10:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ICM-Qwen2-VL-2B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fd1d7c7 --- /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 +ICM-Qwen2-VL-2B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ICM-Qwen2-VL-2B.i1-IQ1_M.gguf b/ICM-Qwen2-VL-2B.i1-IQ1_M.gguf new file mode 100644 index 0000000..9059797 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fdd6fdce059cbebb720c6a9c99b51d8e23e501307fb8908beba964ba2d62d5 +size 464460448 diff --git a/ICM-Qwen2-VL-2B.i1-IQ1_S.gguf b/ICM-Qwen2-VL-2B.i1-IQ1_S.gguf new file mode 100644 index 0000000..8056e9d --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63b6764863e3f01611b6884076261c13109ea6f83ec110328dca49a0565f5ea4 +size 436526752 diff --git a/ICM-Qwen2-VL-2B.i1-IQ2_M.gguf b/ICM-Qwen2-VL-2B.i1-IQ2_M.gguf new file mode 100644 index 0000000..ce9b95d --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05609c584bd71bf725f790154cb9f5e2720577fea9627d29172e8462a53f48f5 +size 601053856 diff --git a/ICM-Qwen2-VL-2B.i1-IQ2_S.gguf b/ICM-Qwen2-VL-2B.i1-IQ2_S.gguf new file mode 100644 index 0000000..e83e704 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3271795ea1d640daac6a56a276f28d432c2ee87eaa66ebe361be0184e885f677 +size 563808928 diff --git a/ICM-Qwen2-VL-2B.i1-IQ2_XS.gguf b/ICM-Qwen2-VL-2B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..48ea09d --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9f60cfb1098cf2a312517f393568dd30516dffe69340b918721102a4c2e216 +size 550325920 diff --git a/ICM-Qwen2-VL-2B.i1-IQ2_XXS.gguf b/ICM-Qwen2-VL-2B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8fb66d5 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76019519792dc9c63b665a79031a608acb38190c8158950c9dede7ded5ef73ee +size 511016608 diff --git a/ICM-Qwen2-VL-2B.i1-IQ3_M.gguf b/ICM-Qwen2-VL-2B.i1-IQ3_M.gguf new file mode 100644 index 0000000..89a8274 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed8233eaaa2adb6c46b546ff85079e1794dfe9067cf589702afb5c8e4d896f0 +size 776663200 diff --git a/ICM-Qwen2-VL-2B.i1-IQ3_S.gguf b/ICM-Qwen2-VL-2B.i1-IQ3_S.gguf new file mode 100644 index 0000000..a148270 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767ce7e62ce77e1fbbf170f381bdba600799fb7b155a52008055a448d2b9d9f4 +size 762406048 diff --git a/ICM-Qwen2-VL-2B.i1-IQ3_XS.gguf b/ICM-Qwen2-VL-2B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cdb4008 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d6ede752cbbc2c1cef9919fc077a5372e781626f55340760e49d9ad75859b8 +size 731698336 diff --git a/ICM-Qwen2-VL-2B.i1-IQ3_XXS.gguf b/ICM-Qwen2-VL-2B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..58d55ae --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e1f46767e41f573b8f1f169eea3143382116bc89fcc68856e9e8639f349e6a +size 668791456 diff --git a/ICM-Qwen2-VL-2B.i1-IQ4_NL.gguf b/ICM-Qwen2-VL-2B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..25de5fa --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df8cfbd5ffd2b7f86b919b40dab68b3ba46d3ba55352a820ff4ddc67c135e4d +size 936330400 diff --git a/ICM-Qwen2-VL-2B.i1-IQ4_XS.gguf b/ICM-Qwen2-VL-2B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f63b620 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc3160026d6dee52756b3fc16a3e4e494daec04138524c5dfe066c34634a7e2 +size 895730848 diff --git a/ICM-Qwen2-VL-2B.i1-Q2_K.gguf b/ICM-Qwen2-VL-2B.i1-Q2_K.gguf new file mode 100644 index 0000000..046d323 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e2a31ba921e137f72343e0f0504da4dee3a29dfdb8a2f3bd5a1e12c9946fff +size 676304032 diff --git a/ICM-Qwen2-VL-2B.i1-Q2_K_S.gguf b/ICM-Qwen2-VL-2B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0637ec4 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a1a410327b1eacb42c6781f4ce4d83ac7ebed7c5c38ea3ab746217983056df +size 640134304 diff --git a/ICM-Qwen2-VL-2B.i1-Q3_K_L.gguf b/ICM-Qwen2-VL-2B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1442f8e --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4404800aca508b90aa93742257e7e51ade8aa6d9cd3faa152e14a43a0176c1 +size 880161952 diff --git a/ICM-Qwen2-VL-2B.i1-Q3_K_M.gguf b/ICM-Qwen2-VL-2B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..965ad08 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a659e9c882dbda519ed1f0c2d65abacd3d5f5fe37e9499a90e90ea25fd4e41b +size 824177824 diff --git a/ICM-Qwen2-VL-2B.i1-Q3_K_S.gguf b/ICM-Qwen2-VL-2B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c5eb557 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa4543167ea9a34a5a810f7929d8c81f5d7373db4924ded2bea16cf7a71eb25 +size 760943776 diff --git a/ICM-Qwen2-VL-2B.i1-Q4_0.gguf b/ICM-Qwen2-VL-2B.i1-Q4_0.gguf new file mode 100644 index 0000000..b22d087 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88eac5197db795373ce0cb5957c6ed6a2d44342d982a541d56029d66392f0a73 +size 937534624 diff --git a/ICM-Qwen2-VL-2B.i1-Q4_1.gguf b/ICM-Qwen2-VL-2B.i1-Q4_1.gguf new file mode 100644 index 0000000..5cf6781 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77641295a3a7c76d0c58e80de65232505e7b100e43e59aa04086fbff1ba6856b +size 1016841376 diff --git a/ICM-Qwen2-VL-2B.i1-Q4_K_M.gguf b/ICM-Qwen2-VL-2B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..931db28 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa5ff6f9df68f23b8f896ca7391e3f991b3ffe4a496551b6bb5ef46b77e0a7b +size 986047648 diff --git a/ICM-Qwen2-VL-2B.i1-Q4_K_S.gguf b/ICM-Qwen2-VL-2B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4ce3868 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de27aae69d909d571823c748d8c04607eeb043e8dcda8199135b902ce24f7ef8 +size 940311712 diff --git a/ICM-Qwen2-VL-2B.i1-Q5_K_M.gguf b/ICM-Qwen2-VL-2B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..431b596 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4955b0639d190a79a42dd5d4b58a5708871b26c52261150215bf9dd3cc70e11e +size 1125049504 diff --git a/ICM-Qwen2-VL-2B.i1-Q5_K_S.gguf b/ICM-Qwen2-VL-2B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7e85972 --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744ca5b235a4219a5e8df1232b8405061921ec6443e29d4e418a999fe38e26de +size 1098728608 diff --git a/ICM-Qwen2-VL-2B.i1-Q6_K.gguf b/ICM-Qwen2-VL-2B.i1-Q6_K.gguf new file mode 100644 index 0000000..0e545ad --- /dev/null +++ b/ICM-Qwen2-VL-2B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05dc3f512aa3dd176f32a971e91bb8f748526ff7b4782bba0506bada456e680e +size 1272738976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4da5016 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: zhaoyuzhi/ICM-Qwen2-VL-2B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/zhaoyuzhi/ICM-Qwen2-VL-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ICM-Qwen2-VL-2B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-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/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-i1-GGUF/resolve/main/ICM-Qwen2-VL-2B.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1dc8566 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c49e06b5c8bd745db9814985417e706cdf915b88a3be666b4e089a2f42909f +size 2042201