commit 5430b2b20e5195ac45a247237069d1d6a82c4deb Author: ModelHub XC Date: Wed Jul 29 02:59:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-8B-V3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02a6ec5 --- /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-8B-V3.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-V3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-V3.IQ4_XS.gguf b/Qwen3-VL-8B-V3.IQ4_XS.gguf new file mode 100644 index 0000000..3aa6b05 --- /dev/null +++ b/Qwen3-VL-8B-V3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df9951aa179890d9dc6a55aa15ebfee8eedc546f48072f0c1a3fcbe4bfc5e4e +size 4593297920 diff --git a/Qwen3-VL-8B-V3.Q2_K.gguf b/Qwen3-VL-8B-V3.Q2_K.gguf new file mode 100644 index 0000000..ef4470b --- /dev/null +++ b/Qwen3-VL-8B-V3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db86c2aa35012a56bf1b9838aed14c2d73cc7454dcf50909bfc001c5b1991620 +size 3281734144 diff --git a/Qwen3-VL-8B-V3.Q3_K_L.gguf b/Qwen3-VL-8B-V3.Q3_K_L.gguf new file mode 100644 index 0000000..ce3ed99 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2760c4af7f0a0bdd9acc36f488c933f0d9256fdb4af2ae8227c0c752d4fb62c0 +size 4431395328 diff --git a/Qwen3-VL-8B-V3.Q3_K_M.gguf b/Qwen3-VL-8B-V3.Q3_K_M.gguf new file mode 100644 index 0000000..2b6edde --- /dev/null +++ b/Qwen3-VL-8B-V3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657965f1592b5fc441686e2bfdc53435ef334394a45ea51fe925037a8900e203 +size 4124162560 diff --git a/Qwen3-VL-8B-V3.Q3_K_S.gguf b/Qwen3-VL-8B-V3.Q3_K_S.gguf new file mode 100644 index 0000000..6059ac9 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c75f0c71263b283b2c798c57822a1c78e9091593b6cb4c22c08668891d974581 +size 3769612800 diff --git a/Qwen3-VL-8B-V3.Q4_K_M.gguf b/Qwen3-VL-8B-V3.Q4_K_M.gguf new file mode 100644 index 0000000..238fb1e --- /dev/null +++ b/Qwen3-VL-8B-V3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24572c137978b1b6b5db0fe2713ecc5dbcc02be70645c14b9f359917b1cb5ae0 +size 5027785216 diff --git a/Qwen3-VL-8B-V3.Q4_K_S.gguf b/Qwen3-VL-8B-V3.Q4_K_S.gguf new file mode 100644 index 0000000..c4f9d66 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1825e83eca827cbeb3445df837a7de665ea7166dd9157422c25e313362335cde +size 4802013696 diff --git a/Qwen3-VL-8B-V3.Q5_K_M.gguf b/Qwen3-VL-8B-V3.Q5_K_M.gguf new file mode 100644 index 0000000..2ee55f6 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a781e338777f938bdac8753121784656b236b037204e4b401eb4d1d7cd612b3 +size 5851113984 diff --git a/Qwen3-VL-8B-V3.Q5_K_S.gguf b/Qwen3-VL-8B-V3.Q5_K_S.gguf new file mode 100644 index 0000000..4153ef2 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e988a79a261523a75485d1b5d7ba764c97bd06b432c04f2c0f92e1511bec60b4 +size 5720762880 diff --git a/Qwen3-VL-8B-V3.Q6_K.gguf b/Qwen3-VL-8B-V3.Q6_K.gguf new file mode 100644 index 0000000..98b8171 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91b7d392d9da9a3b9cbbf0294de08261fe9fb6eca2ef5fcb615eed5f99cec60 +size 6725900800 diff --git a/Qwen3-VL-8B-V3.Q8_0.gguf b/Qwen3-VL-8B-V3.Q8_0.gguf new file mode 100644 index 0000000..9627854 --- /dev/null +++ b/Qwen3-VL-8B-V3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88a1640890097b4997f3320490d1478d9cea2c7975937762611f183ca96e7c6d +size 8709519872 diff --git a/Qwen3-VL-8B-V3.f16.gguf b/Qwen3-VL-8B-V3.f16.gguf new file mode 100644 index 0000000..b02b361 --- /dev/null +++ b/Qwen3-VL-8B-V3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18293bfae175baaece3788fb6f42d6098fbd4e8435bb486f30eb286cfe8817a +size 16388045312 diff --git a/Qwen3-VL-8B-V3.mmproj-Q8_0.gguf b/Qwen3-VL-8B-V3.mmproj-Q8_0.gguf new file mode 100644 index 0000000..fee6622 --- /dev/null +++ b/Qwen3-VL-8B-V3.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5979c5364fc41efa13ef886adcfc84c95b725d7c2bbc8fdd3dcfe5dae5759d3 +size 752289760 diff --git a/Qwen3-VL-8B-V3.mmproj-f16.gguf b/Qwen3-VL-8B-V3.mmproj-f16.gguf new file mode 100644 index 0000000..64ae32f --- /dev/null +++ b/Qwen3-VL-8B-V3.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c40972dae39b7efb6553d6bfc5281fb0ab415658cf10a5fdd7dc62f3f2d644 +size 1159029856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..268a617 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Zaynoid/Qwen3-VL-8B-V3 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Zaynoid/Qwen3-VL-8B-V3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-V3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-i1-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-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-V3-GGUF/resolve/main/Qwen3-VL-8B-V3.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. + +