commit 3b6f163598faf0f97108decc02cd4fc6d10067c0 Author: ModelHub XC Date: Fri Jul 24 03:06:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc99a8f --- /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-2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-2B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-2B-Instruct.IQ4_XS.gguf b/Qwen3-VL-2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..c8c34fb --- /dev/null +++ b/Qwen3-VL-2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f965185949fadb5b4eed4a12a548f82b3c7fe803a8177238d67f70f9a15a273 +size 1016282624 diff --git a/Qwen3-VL-2B-Instruct.Q2_K.gguf b/Qwen3-VL-2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..bec39fc --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f372a3f4c2fa8633bffce70f3d550aadde8dc7d001d823e49182d0513c276f9a +size 777797120 diff --git a/Qwen3-VL-2B-Instruct.Q3_K_L.gguf b/Qwen3-VL-2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..88b0b87 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0396aa31456b2b33de7ac600b989a998f90d9d4f9aa3a8f2e5674b0b6fc364 +size 1003503104 diff --git a/Qwen3-VL-2B-Instruct.Q3_K_M.gguf b/Qwen3-VL-2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..813e792 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01d443cff828641cbab3ddacfd82cccf4759136852366f4fa3b849b9dd05aad +size 939539968 diff --git a/Qwen3-VL-2B-Instruct.Q3_K_S.gguf b/Qwen3-VL-2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..d502b13 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ede4e5c6fc04b23b5ba45da23116dadeb204b76703b9d8edff69e20bc62d6f +size 867253760 diff --git a/Qwen3-VL-2B-Instruct.Q4_K_M.gguf b/Qwen3-VL-2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7082690 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5941142ae48646fa46cad3c2ba5a44e6a205b66a93fe7d3d65aa119560331d8 +size 1107410432 diff --git a/Qwen3-VL-2B-Instruct.Q4_K_S.gguf b/Qwen3-VL-2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..ebe03bb --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ca37f77fe8bed1f13a11bbc06de0f5306364bc0a26a3a539b3c37b56681418 +size 1060191744 diff --git a/Qwen3-VL-2B-Instruct.Q5_K_M.gguf b/Qwen3-VL-2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bcc69f2 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3954f2f09c48ca90ee44266c99ffcd98d82e4590df098d9fc7f1995f0876a04a +size 1257881088 diff --git a/Qwen3-VL-2B-Instruct.Q5_K_S.gguf b/Qwen3-VL-2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..64613ae --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcffe6a69ffba7ca5c6a4976399f865d2c73cd4e5730200400c850fe18a53389 +size 1230585344 diff --git a/Qwen3-VL-2B-Instruct.Q6_K.gguf b/Qwen3-VL-2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..4e8253a --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc08c2464bf690d4401c339fb5369ab8378f5b103058fd40ec74da24711e5f2 +size 1417756160 diff --git a/Qwen3-VL-2B-Instruct.Q8_0.gguf b/Qwen3-VL-2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a57e22b --- /dev/null +++ b/Qwen3-VL-2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c4576433988e36f5d916834d6603259d803c53ddc1d486c30a2d45d3f15ec5 +size 1834427904 diff --git a/Qwen3-VL-2B-Instruct.f16.gguf b/Qwen3-VL-2B-Instruct.f16.gguf new file mode 100644 index 0000000..bf60b67 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619add06bf58ce311728b1cb5191a418b6c3051e60f8271aef6d1d050f8293d7 +size 3447350784 diff --git a/Qwen3-VL-2B-Instruct.mmproj-Q8_0.gguf b/Qwen3-VL-2B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..bb3bcb1 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d315ee769241c1bede31a13db24ce89870e1c8f5f8358aba52f17d2e3fa2c9fa +size 445053216 diff --git a/Qwen3-VL-2B-Instruct.mmproj-f16.gguf b/Qwen3-VL-2B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..47e2f95 --- /dev/null +++ b/Qwen3-VL-2B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3f6a56979a1ce7056b9a20be6cf6b6f6ad4837aa3da532b5afcfcfd1faa38b +size 819394848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a82b0f --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Qwen/Qwen3-VL-2B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-2B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-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-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3-VL-2B-Instruct.f16.gguf) | f16 | 3.5 | 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. + +