commit 85f4e5cdf364840440d62810d0f9e96933a8fa64 Author: ModelHub XC Date: Thu Jul 23 04:19:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-Augment-v3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..831d159 --- /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-Augment-v3.1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Augment-v3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-Augment-v3.1.IQ4_XS.gguf b/Qwen3-VL-Augment-v3.1.IQ4_XS.gguf new file mode 100644 index 0000000..beb58cd --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320c45fbf2f68de626f42b539880007f9f756506d96669dcd430ccbf6bb117f4 +size 4593297952 diff --git a/Qwen3-VL-Augment-v3.1.Q2_K.gguf b/Qwen3-VL-Augment-v3.1.Q2_K.gguf new file mode 100644 index 0000000..2aa0d5e --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfc7c4d8f86c640b27a7d8b25006288576ed2e4585cbb6d115ddf96344d4ae8 +size 3281734176 diff --git a/Qwen3-VL-Augment-v3.1.Q3_K_L.gguf b/Qwen3-VL-Augment-v3.1.Q3_K_L.gguf new file mode 100644 index 0000000..d1ee8de --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2383957e73f891951ab44e794fdc362a99b84d154ddd8dabcdf42df1dbac6de6 +size 4431395360 diff --git a/Qwen3-VL-Augment-v3.1.Q3_K_M.gguf b/Qwen3-VL-Augment-v3.1.Q3_K_M.gguf new file mode 100644 index 0000000..05860c4 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1bf713df9e657c70b2d83fd27b9a0d1676fc7b6a241d192dcc5a88fc8056c4f +size 4124162592 diff --git a/Qwen3-VL-Augment-v3.1.Q3_K_S.gguf b/Qwen3-VL-Augment-v3.1.Q3_K_S.gguf new file mode 100644 index 0000000..8df7423 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334c232dae6912c78be5fe32068abfa94fe67479fb14e3ab7e78a68c16b7aefc +size 3769612832 diff --git a/Qwen3-VL-Augment-v3.1.Q4_K_M.gguf b/Qwen3-VL-Augment-v3.1.Q4_K_M.gguf new file mode 100644 index 0000000..a913e45 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806aa9548576dc27cb4f557b362ae295cd6c160b60af3a083a8095c32995e6a1 +size 5027785248 diff --git a/Qwen3-VL-Augment-v3.1.Q4_K_S.gguf b/Qwen3-VL-Augment-v3.1.Q4_K_S.gguf new file mode 100644 index 0000000..a5209d7 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230a57e4f30fbcbf78bad2a4a2eb46c5639aef652228f67c4dc54c71de76b369 +size 4802013728 diff --git a/Qwen3-VL-Augment-v3.1.Q5_K_M.gguf b/Qwen3-VL-Augment-v3.1.Q5_K_M.gguf new file mode 100644 index 0000000..f354c35 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b07179516b64163cd8af4c6fe2f3e76415df2cff71d4715c1532275684ca51a +size 5851114016 diff --git a/Qwen3-VL-Augment-v3.1.Q5_K_S.gguf b/Qwen3-VL-Augment-v3.1.Q5_K_S.gguf new file mode 100644 index 0000000..cb8160c --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df350e54529858bf69907bc8377dc50b4ee9b53c816037862f8a0d0037b24be +size 5720762912 diff --git a/Qwen3-VL-Augment-v3.1.Q6_K.gguf b/Qwen3-VL-Augment-v3.1.Q6_K.gguf new file mode 100644 index 0000000..add63e0 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0eae3577f57eac6d07308a0363284c00303dce70cf3ced472698a45505b955 +size 6725900832 diff --git a/Qwen3-VL-Augment-v3.1.Q8_0.gguf b/Qwen3-VL-Augment-v3.1.Q8_0.gguf new file mode 100644 index 0000000..0b7c565 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e330705f828aa68c1e06b53a6402b8ea6943c3c96c670ee7137358af599024e2 +size 8709519904 diff --git a/Qwen3-VL-Augment-v3.1.f16.gguf b/Qwen3-VL-Augment-v3.1.f16.gguf new file mode 100644 index 0000000..b0d28d7 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5cc354a63bb6f607004152e60200eb9e82529ab4be472ec1b1d4789da3a298 +size 16388045344 diff --git a/Qwen3-VL-Augment-v3.1.mmproj-Q8_0.gguf b/Qwen3-VL-Augment-v3.1.mmproj-Q8_0.gguf new file mode 100644 index 0000000..4da61f0 --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d72e41ade1373e72047d8aebc03d01ca7a16f3acec29cf5ce3d2f0ee66148a +size 752289728 diff --git a/Qwen3-VL-Augment-v3.1.mmproj-f16.gguf b/Qwen3-VL-Augment-v3.1.mmproj-f16.gguf new file mode 100644 index 0000000..46b3a1b --- /dev/null +++ b/Qwen3-VL-Augment-v3.1.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9014579faa3ae499d488b1b0939026b93e527e1dc4ce4f14523e97946f992a +size 1159029824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f78495d --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: brownyeyez/Qwen3-VL-Augment-v3.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/brownyeyez/Qwen3-VL-Augment-v3.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-Augment-v3.1-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-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Augment-v3.1-GGUF/resolve/main/Qwen3-VL-Augment-v3.1.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. + +