commit 5f481f005c6ca8d7e4251ae7a3bc5d521f18e385 Author: ModelHub XC Date: Fri Oct 2 02:43:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-vl-flux2-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef2476a --- /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 +qwen3-vl-flux2-8b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-vl-flux2-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8964959 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: deepglugs/qwen3-vl-flux2-8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vision-language +- multimodal +--- +## About + + + + + + + + + +static quants of https://huggingface.co/deepglugs/qwen3-vl-flux2-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-vl-flux2-8b-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/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-vl-flux2-8b-GGUF/resolve/main/qwen3-vl-flux2-8b.f16.gguf) | f16 | 16.5 | 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. + + diff --git a/qwen3-vl-flux2-8b.IQ4_XS.gguf b/qwen3-vl-flux2-8b.IQ4_XS.gguf new file mode 100644 index 0000000..13d5155 --- /dev/null +++ b/qwen3-vl-flux2-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7bf2aa1c1c066a779cbcef75c53608282ab0f85b127b366bc8adfbd7a0bd14 +size 4593298400 diff --git a/qwen3-vl-flux2-8b.Q2_K.gguf b/qwen3-vl-flux2-8b.Q2_K.gguf new file mode 100644 index 0000000..6ea7c31 --- /dev/null +++ b/qwen3-vl-flux2-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ff6d9f0112ae882653296415ca4461ce0526e0aecb3778a8faaec824a86379b +size 3281734624 diff --git a/qwen3-vl-flux2-8b.Q3_K_L.gguf b/qwen3-vl-flux2-8b.Q3_K_L.gguf new file mode 100644 index 0000000..e42bed8 --- /dev/null +++ b/qwen3-vl-flux2-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dea51b4c528c42b2298dbe019997578bc77d624885b48b3326941a6037cffb9 +size 4431395808 diff --git a/qwen3-vl-flux2-8b.Q3_K_M.gguf b/qwen3-vl-flux2-8b.Q3_K_M.gguf new file mode 100644 index 0000000..267f93e --- /dev/null +++ b/qwen3-vl-flux2-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2627e577ca286d8e1a530395e5d3043f8009c7cbe073c87b9de53dcb825f7a15 +size 4124163040 diff --git a/qwen3-vl-flux2-8b.Q3_K_S.gguf b/qwen3-vl-flux2-8b.Q3_K_S.gguf new file mode 100644 index 0000000..d9e6be6 --- /dev/null +++ b/qwen3-vl-flux2-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b74fe2e8c042cc0799a367bc8712b82827c51e800b0dae3749045a339268d2 +size 3769613280 diff --git a/qwen3-vl-flux2-8b.Q4_K_M.gguf b/qwen3-vl-flux2-8b.Q4_K_M.gguf new file mode 100644 index 0000000..121a4dd --- /dev/null +++ b/qwen3-vl-flux2-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f3a67060303c1fb3b7aa895dfecdc70afa7f7a541bb2064d0bf0e707372701 +size 5027785696 diff --git a/qwen3-vl-flux2-8b.Q4_K_S.gguf b/qwen3-vl-flux2-8b.Q4_K_S.gguf new file mode 100644 index 0000000..5726abf --- /dev/null +++ b/qwen3-vl-flux2-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c34734f7463586791e4e4fe6cea581a7ff4b1735c4c7630f43b235bad4f55e +size 4802014176 diff --git a/qwen3-vl-flux2-8b.Q5_K_M.gguf b/qwen3-vl-flux2-8b.Q5_K_M.gguf new file mode 100644 index 0000000..880ff8a --- /dev/null +++ b/qwen3-vl-flux2-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8000ae74d451b7e89dca7a9c7ca7785b72761fbefc2808a3d3d06582de23de4d +size 5851114464 diff --git a/qwen3-vl-flux2-8b.Q5_K_S.gguf b/qwen3-vl-flux2-8b.Q5_K_S.gguf new file mode 100644 index 0000000..070c9a2 --- /dev/null +++ b/qwen3-vl-flux2-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d2e5a6400c53b82d598721ca10e72916e323a7b65e03a1172a7268e40eeb15 +size 5720763360 diff --git a/qwen3-vl-flux2-8b.Q6_K.gguf b/qwen3-vl-flux2-8b.Q6_K.gguf new file mode 100644 index 0000000..a43be6b --- /dev/null +++ b/qwen3-vl-flux2-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b4bdb319d9036e77b99bb9520c0a6c379e877864d0aa48c3623265513ab2d8 +size 6725901280 diff --git a/qwen3-vl-flux2-8b.Q8_0.gguf b/qwen3-vl-flux2-8b.Q8_0.gguf new file mode 100644 index 0000000..20ebf67 --- /dev/null +++ b/qwen3-vl-flux2-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b5f59f87f9ef8a3ab9e282f586e0bc5f7e0ce340e4afcde2867ddd83a36abd +size 8709520352 diff --git a/qwen3-vl-flux2-8b.f16.gguf b/qwen3-vl-flux2-8b.f16.gguf new file mode 100644 index 0000000..40b0827 --- /dev/null +++ b/qwen3-vl-flux2-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1c0457dc93c9c122f4f6febe175ae700f383f4412bd753d5ab70306ac18569 +size 16388045792 diff --git a/qwen3-vl-flux2-8b.mmproj-Q8_0.gguf b/qwen3-vl-flux2-8b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..e5a81eb --- /dev/null +++ b/qwen3-vl-flux2-8b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a244e4a4322776d4f525a6f02bbe71bef6cd380ce40224ef1f1c81bdcbdaa942 +size 752290208 diff --git a/qwen3-vl-flux2-8b.mmproj-f16.gguf b/qwen3-vl-flux2-8b.mmproj-f16.gguf new file mode 100644 index 0000000..32ae5c8 --- /dev/null +++ b/qwen3-vl-flux2-8b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756fefb794dea397efc97d0e8ba524f2269041259ea1fe15856377f412fafe8b +size 1159030304