commit 391f12ec66ba8a3e4f152a8f269ad74a544e0507 Author: ModelHub XC Date: Tue Jul 21 04:13:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3vl8b-finetune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52bfabf --- /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 +qwen3vl8b-finetune.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3vl8b-finetune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..460a03d --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: om-ai/qwen3vl8b-finetune +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3_vl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/om-ai/qwen3vl8b-finetune + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3vl8b-finetune-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/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3vl8b-finetune-GGUF/resolve/main/qwen3vl8b-finetune.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/qwen3vl8b-finetune.IQ4_XS.gguf b/qwen3vl8b-finetune.IQ4_XS.gguf new file mode 100644 index 0000000..5b4b6ee --- /dev/null +++ b/qwen3vl8b-finetune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fe94b03ed26276bdf7d8c52eacadad677fbe4d150fcfdd91afa120c1b27413 +size 4593298336 diff --git a/qwen3vl8b-finetune.Q2_K.gguf b/qwen3vl8b-finetune.Q2_K.gguf new file mode 100644 index 0000000..21f82a0 --- /dev/null +++ b/qwen3vl8b-finetune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eccb8449b56c35871e5767f7fed80239a820cd0f9ddab3c12ff2765707b6fee +size 3281734560 diff --git a/qwen3vl8b-finetune.Q3_K_L.gguf b/qwen3vl8b-finetune.Q3_K_L.gguf new file mode 100644 index 0000000..f874108 --- /dev/null +++ b/qwen3vl8b-finetune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c912935a01c170b881a4307489328b2a76d08079f71690cf93a1048befdffe +size 4431395744 diff --git a/qwen3vl8b-finetune.Q3_K_M.gguf b/qwen3vl8b-finetune.Q3_K_M.gguf new file mode 100644 index 0000000..b475e0f --- /dev/null +++ b/qwen3vl8b-finetune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d89e4638638b0e5f11eed2b5f89142faa419c50ee5c1ce3dd5a74d59023fac +size 4124162976 diff --git a/qwen3vl8b-finetune.Q3_K_S.gguf b/qwen3vl8b-finetune.Q3_K_S.gguf new file mode 100644 index 0000000..cd75456 --- /dev/null +++ b/qwen3vl8b-finetune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb55e8b37d0f8a5317ec3bf6845173116856ed3148c765a08e918b5ceff1a3fd +size 3769613216 diff --git a/qwen3vl8b-finetune.Q4_K_M.gguf b/qwen3vl8b-finetune.Q4_K_M.gguf new file mode 100644 index 0000000..92d3db7 --- /dev/null +++ b/qwen3vl8b-finetune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebeb8de73c7d771ba23a63229cc312ef31080c4fb00183052463a97937dd5ba +size 5027785632 diff --git a/qwen3vl8b-finetune.Q4_K_S.gguf b/qwen3vl8b-finetune.Q4_K_S.gguf new file mode 100644 index 0000000..1c93ad3 --- /dev/null +++ b/qwen3vl8b-finetune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9e9b792332bddf67b45a7fe532e4e71ff54b740209d434001fad0b86159155 +size 4802014112 diff --git a/qwen3vl8b-finetune.Q5_K_M.gguf b/qwen3vl8b-finetune.Q5_K_M.gguf new file mode 100644 index 0000000..7c798ca --- /dev/null +++ b/qwen3vl8b-finetune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae4a58405590aba2a816d60a30f01b5754c06128b0f1cfbaaa14365156fbf6d +size 5851114400 diff --git a/qwen3vl8b-finetune.Q5_K_S.gguf b/qwen3vl8b-finetune.Q5_K_S.gguf new file mode 100644 index 0000000..70e8759 --- /dev/null +++ b/qwen3vl8b-finetune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66effe731c3b88f2b611055df73c9c21703fa08db7a3ce329e828a428576da4d +size 5720763296 diff --git a/qwen3vl8b-finetune.Q6_K.gguf b/qwen3vl8b-finetune.Q6_K.gguf new file mode 100644 index 0000000..3198163 --- /dev/null +++ b/qwen3vl8b-finetune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1003cc1960239f9cffbfdee6212737efcfbbb819e5a2096a91a4b629e6ae4a6 +size 6725901216 diff --git a/qwen3vl8b-finetune.Q8_0.gguf b/qwen3vl8b-finetune.Q8_0.gguf new file mode 100644 index 0000000..d8eda84 --- /dev/null +++ b/qwen3vl8b-finetune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68dad725deda3fea238fc1da4777edb763300a747335614e262b6ef7ce196ad +size 8709520288 diff --git a/qwen3vl8b-finetune.f16.gguf b/qwen3vl8b-finetune.f16.gguf new file mode 100644 index 0000000..94003f3 --- /dev/null +++ b/qwen3vl8b-finetune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863d2c6dfad2a65d3b53c9eae817ad728c37f495b06e4782aea4a8f5d954c05a +size 16388045728 diff --git a/qwen3vl8b-finetune.mmproj-Q8_0.gguf b/qwen3vl8b-finetune.mmproj-Q8_0.gguf new file mode 100644 index 0000000..bc9ddc2 --- /dev/null +++ b/qwen3vl8b-finetune.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7add613d5ec756637a89bf2d84c52f234ba469cf88082d5602b013f4848938 +size 752290112 diff --git a/qwen3vl8b-finetune.mmproj-f16.gguf b/qwen3vl8b-finetune.mmproj-f16.gguf new file mode 100644 index 0000000..c560d22 --- /dev/null +++ b/qwen3vl8b-finetune.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b93b6ab4577380ed220405add56499aaf63b1f80e499dc380ef609562f5cc0 +size 1159030208