commit 5013f2d86067f2468d7b5c68dc885868060a40ef Author: ModelHub XC Date: Sat May 30 12:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CapRL-Qwen3VL-4B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..19e1fcf --- /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 +CapRL-Qwen3VL-4B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CapRL-Qwen3VL-4B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CapRL-Qwen3VL-4B.i1-IQ1_M.gguf b/CapRL-Qwen3VL-4B.i1-IQ1_M.gguf new file mode 100644 index 0000000..3367392 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4423886e0c221877619f43ef2583f131328ef9c29a4d8b431a544bc1e9198e +size 1254646048 diff --git a/CapRL-Qwen3VL-4B.i1-IQ1_S.gguf b/CapRL-Qwen3VL-4B.i1-IQ1_S.gguf new file mode 100644 index 0000000..475df32 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744884ed9a15bb5060ba9435781055d1dbf2933992cd388683c6c2c9c33f2cec +size 1182884128 diff --git a/CapRL-Qwen3VL-4B.i1-IQ2_M.gguf b/CapRL-Qwen3VL-4B.i1-IQ2_M.gguf new file mode 100644 index 0000000..a9e8f7e --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b9424dba846d84eb0879fffb777afe6dbad6440170410fac594ec9e97287bd +size 1680115488 diff --git a/CapRL-Qwen3VL-4B.i1-IQ2_S.gguf b/CapRL-Qwen3VL-4B.i1-IQ2_S.gguf new file mode 100644 index 0000000..eaf5609 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c3bf069fbcd12c84141486737871eebbdac0f77459f00864171ff9890bab00 +size 1584432928 diff --git a/CapRL-Qwen3VL-4B.i1-IQ2_XS.gguf b/CapRL-Qwen3VL-4B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..62042b2 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de60a29c0b5d5fceaf2f8b32067c3e338e64d0caa6a395a2a71d903eeb792e4d +size 1481728288 diff --git a/CapRL-Qwen3VL-4B.i1-IQ2_XXS.gguf b/CapRL-Qwen3VL-4B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..75fdda9 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b594cdf68964acd2e73fce538234223af0fe96abcd3559d19ac3c7611e67ba9 +size 1374249248 diff --git a/CapRL-Qwen3VL-4B.i1-IQ3_M.gguf b/CapRL-Qwen3VL-4B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c8d9bb9 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946625e30d6a3dacc908c8b2c02898e377167055c025ca928ded73f682f0e6cc +size 2130027808 diff --git a/CapRL-Qwen3VL-4B.i1-IQ3_S.gguf b/CapRL-Qwen3VL-4B.i1-IQ3_S.gguf new file mode 100644 index 0000000..2c65469 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4f945b74653f1ce5685df6280f3d190325353f9bbe0f7a0058056afe45e7b5 +size 2066662688 diff --git a/CapRL-Qwen3VL-4B.i1-IQ3_XS.gguf b/CapRL-Qwen3VL-4B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1bddf3f --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512021af0a1c14cecfd96d4f56adb598dca9bbde363b56cf58dd53dcaa9c32fc +size 1981506848 diff --git a/CapRL-Qwen3VL-4B.i1-IQ3_XXS.gguf b/CapRL-Qwen3VL-4B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..40ae99a --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912de37110c646d2481d1537b707661485fad8dbfda184c29cf62ff49420051b +size 1837319968 diff --git a/CapRL-Qwen3VL-4B.i1-IQ4_NL.gguf b/CapRL-Qwen3VL-4B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..de8e86c --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f8bea0bf0bed8233d67b86ff5b494613855be811647c6a247792d84b5fd1a9 +size 2600133408 diff --git a/CapRL-Qwen3VL-4B.i1-IQ4_XS.gguf b/CapRL-Qwen3VL-4B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1414b63 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae4a719af03e0315069ba6d0054942b2fc667dd07ad1db0472a1bbb084e2229 +size 2477386528 diff --git a/CapRL-Qwen3VL-4B.i1-Q2_K.gguf b/CapRL-Qwen3VL-4B.i1-Q2_K.gguf new file mode 100644 index 0000000..12f48d4 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97346e0fc9d2cdedacf74c70a2bdeaf43538b586a7b0c9ce44554be8e3e1d5b +size 1797127968 diff --git a/CapRL-Qwen3VL-4B.i1-Q2_K_S.gguf b/CapRL-Qwen3VL-4B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..2cf1c43 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d8178b5d7dda9dec8fc4790cbaf4c7e897d8a3288aaf7569e11c1e5498b68e +size 1691082528 diff --git a/CapRL-Qwen3VL-4B.i1-Q3_K_L.gguf b/CapRL-Qwen3VL-4B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2134d61 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e558c29302ef9f17846f72f078af2952ee26f6afe6f20bf2f9c7bb96b3b3340f +size 2406917408 diff --git a/CapRL-Qwen3VL-4B.i1-Q3_K_M.gguf b/CapRL-Qwen3VL-4B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..59133ed --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2530abc6a2c39e632be1254bac03d98f746f868a376e659a5cb042a1d93e12 +size 2242749728 diff --git a/CapRL-Qwen3VL-4B.i1-Q3_K_S.gguf b/CapRL-Qwen3VL-4B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ddd6b7d --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0591af851568bf76fe8668b0ceef250654acbb3b9cd3a76d1c0c298c6c997e2d +size 2054128928 diff --git a/CapRL-Qwen3VL-4B.i1-Q4_0.gguf b/CapRL-Qwen3VL-4B.i1-Q4_0.gguf new file mode 100644 index 0000000..6bb6ee5 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c532551c73a61553b651215ede3e6e74e32df6ed55278ff07a7205d4e5e6701c +size 2594562848 diff --git a/CapRL-Qwen3VL-4B.i1-Q4_1.gguf b/CapRL-Qwen3VL-4B.i1-Q4_1.gguf new file mode 100644 index 0000000..c96b5a0 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3d5e9e1279a68dc801565d03bed79ad9535ce6a31b61b8dcc5ec424951b6dc +size 2839728928 diff --git a/CapRL-Qwen3VL-4B.i1-Q4_K_M.gguf b/CapRL-Qwen3VL-4B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..24527cd --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef3eeaac1217a96a14ed5fdf9209858c087f605992d6c982983d3ffcd41e80d +size 2716070688 diff --git a/CapRL-Qwen3VL-4B.i1-Q4_K_S.gguf b/CapRL-Qwen3VL-4B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f776f1a --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca90cf4a04980dcc42ffbc352f7cc4faca2a2fea0c1c91418906d5b59abcfb6e +size 2602099488 diff --git a/CapRL-Qwen3VL-4B.i1-Q5_K_M.gguf b/CapRL-Qwen3VL-4B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f12fb48 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bd5771bb7df168fa3d3efa90284fb53a719c66366bb6cc3ff67b15e3227f68 +size 3156923168 diff --git a/CapRL-Qwen3VL-4B.i1-Q5_K_S.gguf b/CapRL-Qwen3VL-4B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4258e49 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f1a5ae583b9b916048012c5a11f48aab00c3df129712a3ff756e3c19c21815 +size 3091120928 diff --git a/CapRL-Qwen3VL-4B.i1-Q6_K.gguf b/CapRL-Qwen3VL-4B.i1-Q6_K.gguf new file mode 100644 index 0000000..96b6733 --- /dev/null +++ b/CapRL-Qwen3VL-4B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebad311d77ac98325206de9dea113d57c9b7c089022a13684f38f04c9cc84a40 +size 3625328928 diff --git a/CapRL-Qwen3VL-4B.imatrix.gguf b/CapRL-Qwen3VL-4B.imatrix.gguf new file mode 100644 index 0000000..0ace5d2 --- /dev/null +++ b/CapRL-Qwen3VL-4B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f3df943b1bf4f51ce373e4c17d8d657a5b274dfec31f62a8b2c0803d48fe0b +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d7ed88 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: internlm/CapRL-Qwen3VL-4B +datasets: +- internlm/CapRL-2M +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multimodal +- image caption +- captioning +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/internlm/CapRL-Qwen3VL-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CapRL-Qwen3VL-4B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-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/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q4_1.gguf) | i1-Q4_1 | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CapRL-Qwen3VL-4B-i1-GGUF/resolve/main/CapRL-Qwen3VL-4B.i1-Q6_K.gguf) | i1-Q6_K | 3.7 | 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. + +