commit 650075266c30b16e00b1217a4a12e95d4ab97de5 Author: ModelHub XC Date: Sat Jun 13 22:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AGiXT-Qwen3-VL-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..28af930 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +AGiXT-Qwen3-VL-4B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AGiXT-Qwen3-VL-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AGiXT-Qwen3-VL-4B.IQ4_XS.gguf b/AGiXT-Qwen3-VL-4B.IQ4_XS.gguf new file mode 100644 index 0000000..7b1c399 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93132875ce9439d632dd4cec2298b689fd09005dbfec3b1162eff1d9cb61ecf7 +size 2286318016 diff --git a/AGiXT-Qwen3-VL-4B.Q2_K.gguf b/AGiXT-Qwen3-VL-4B.Q2_K.gguf new file mode 100644 index 0000000..5ace008 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84d092a8c917975f2b03b88f0ce5496b5e0a27b84a4c269b2f5e8cd5f9b6b5b +size 1669501376 diff --git a/AGiXT-Qwen3-VL-4B.Q3_K_L.gguf b/AGiXT-Qwen3-VL-4B.Q3_K_L.gguf new file mode 100644 index 0000000..fcbde24 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe9f9de3825d16ad4c87c49e8dd9536983b94f2f5d0caada7971b853cf33109 +size 2239787456 diff --git a/AGiXT-Qwen3-VL-4B.Q3_K_M.gguf b/AGiXT-Qwen3-VL-4B.Q3_K_M.gguf new file mode 100644 index 0000000..65b5401 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd44bae67063e57e735cc24e60ea0409133863a59317900274f2ae06355bc58 +size 2075619776 diff --git a/AGiXT-Qwen3-VL-4B.Q3_K_S.gguf b/AGiXT-Qwen3-VL-4B.Q3_K_S.gguf new file mode 100644 index 0000000..72dc602 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3d383c552d374b722b4ce2e9962e8944ee7d26dabb802517c687e2f128af14 +size 1886998976 diff --git a/AGiXT-Qwen3-VL-4B.Q4_K_M.gguf b/AGiXT-Qwen3-VL-4B.Q4_K_M.gguf new file mode 100644 index 0000000..b19c58a --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87516ecdb3b5ef004bc7bc1597ee69bab1551d0b336eef89665048b20cd03a4 +size 2497282496 diff --git a/AGiXT-Qwen3-VL-4B.Q4_K_S.gguf b/AGiXT-Qwen3-VL-4B.Q4_K_S.gguf new file mode 100644 index 0000000..14c91e3 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1126c8ec75c68efed2db283207b899a66ca5b9a66517851a01cd4f431d8ac371 +size 2383311296 diff --git a/AGiXT-Qwen3-VL-4B.Q5_K_M.gguf b/AGiXT-Qwen3-VL-4B.Q5_K_M.gguf new file mode 100644 index 0000000..4433dab --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5311d04ca44d2a34743af06fcb51f12e10bd3e61cf911668dd4966d3d996139e +size 2889515456 diff --git a/AGiXT-Qwen3-VL-4B.Q5_K_S.gguf b/AGiXT-Qwen3-VL-4B.Q5_K_S.gguf new file mode 100644 index 0000000..30cc531 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdebf59c268bff0e124e30e25e911de1fc055b6d8b866e3fda8f73e5de1e2ef8 +size 2823713216 diff --git a/AGiXT-Qwen3-VL-4B.Q6_K.gguf b/AGiXT-Qwen3-VL-4B.Q6_K.gguf new file mode 100644 index 0000000..b690ed4 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1680eeb4a508c431474d0b23d95fe6dae0c42e166019461043bca33991997b9a +size 3306262976 diff --git a/AGiXT-Qwen3-VL-4B.Q8_0.gguf b/AGiXT-Qwen3-VL-4B.Q8_0.gguf new file mode 100644 index 0000000..652ff73 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78309f1e6941a40bd38e18202b4b961c90e93a2963ed64b41b65368baf64460c +size 4280406976 diff --git a/AGiXT-Qwen3-VL-4B.f16.gguf b/AGiXT-Qwen3-VL-4B.f16.gguf new file mode 100644 index 0000000..5060096 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7042252579ad373d6028966927c9c3dc706a5d6d086f1ac9e08911e0c6821281 +size 8051286976 diff --git a/AGiXT-Qwen3-VL-4B.mmproj-Q8_0.gguf b/AGiXT-Qwen3-VL-4B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..f6fd388 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4e8e0bdddcdac5c41a2d61074be0dfe67487128b5552128fb36bb73a323f41 +size 453974688 diff --git a/AGiXT-Qwen3-VL-4B.mmproj-f16.gguf b/AGiXT-Qwen3-VL-4B.mmproj-f16.gguf new file mode 100644 index 0000000..7c5c417 --- /dev/null +++ b/AGiXT-Qwen3-VL-4B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:719e0fb7a8aab038e158866bce5f3b5ee1eeda5775781e26cdce4d7804b3ea01 +size 836180640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a1ef6b --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: JoshXT/AGiXT-Qwen3-VL-4B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- agixt +- agent +- fine-tuned +- qwen +- function-calling +- tool-use +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/JoshXT/AGiXT-Qwen3-VL-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AGiXT-Qwen3-VL-4B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AGiXT-Qwen3-VL-4B-GGUF/resolve/main/AGiXT-Qwen3-VL-4B.f16.gguf) | f16 | 8.2 | 16 bpw, overkill | + +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. + +