commit d63e9741ad64b352da7e280262ec4ff92e296eb9 Author: ModelHub XC Date: Thu Jul 16 20:00:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-VL-4B-geez-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba4f2ca --- /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-4B-geez-Base.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-VL-4B-geez-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..85dc722 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: NaolBM/qwen3-VL-4B-geez-Base +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/NaolBM/qwen3-VL-4B-geez-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-VL-4B-geez-Base-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-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q3_K_L.gguf) | Q3_K_L | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q5_K_S.gguf) | Q5_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q6_K.gguf) | Q6_K | 3.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-VL-4B-geez-Base-GGUF/resolve/main/qwen3-VL-4B-geez-Base.f16.gguf) | f16 | 8.3 | 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-4B-geez-Base.IQ4_XS.gguf b/qwen3-VL-4B-geez-Base.IQ4_XS.gguf new file mode 100644 index 0000000..05a754f --- /dev/null +++ b/qwen3-VL-4B-geez-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9613d8afb778712522ef753761d4ba9fbc29927562a5300d53ba7121dafc4387 +size 2332134144 diff --git a/qwen3-VL-4B-geez-Base.Q2_K.gguf b/qwen3-VL-4B-geez-Base.Q2_K.gguf new file mode 100644 index 0000000..8a25c2d --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac87cbff46a45dddf917190c9bba8188da0a714c9fb55cb6dabda29fac57385 +size 1715317504 diff --git a/qwen3-VL-4B-geez-Base.Q3_K_L.gguf b/qwen3-VL-4B-geez-Base.Q3_K_L.gguf new file mode 100644 index 0000000..03e0c37 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88da3a6bd279dd7093dec9bfd69b69469958ad2372461e70c48758dd49440cfb +size 2285603584 diff --git a/qwen3-VL-4B-geez-Base.Q3_K_M.gguf b/qwen3-VL-4B-geez-Base.Q3_K_M.gguf new file mode 100644 index 0000000..783ad16 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4737dbd1593f0b8bac4bbfc6ed8afceef75552a05c7d25c578e3328664a6d366 +size 2121435904 diff --git a/qwen3-VL-4B-geez-Base.Q3_K_S.gguf b/qwen3-VL-4B-geez-Base.Q3_K_S.gguf new file mode 100644 index 0000000..69813f4 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65425f994796a7bbcbec6f78f96722da109a3412d208f51cab13019e26b75651 +size 1932815104 diff --git a/qwen3-VL-4B-geez-Base.Q4_K_M.gguf b/qwen3-VL-4B-geez-Base.Q4_K_M.gguf new file mode 100644 index 0000000..feb1954 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951eb9b35c29ffd6850539a1402a3a2875c7be54c1b734931fbb88be1320c158 +size 2543098624 diff --git a/qwen3-VL-4B-geez-Base.Q4_K_S.gguf b/qwen3-VL-4B-geez-Base.Q4_K_S.gguf new file mode 100644 index 0000000..2e45b40 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211043536c8c10105714766e54c8660e0b91552eac85b7e3ae06c575d62e7434 +size 2429127424 diff --git a/qwen3-VL-4B-geez-Base.Q5_K_M.gguf b/qwen3-VL-4B-geez-Base.Q5_K_M.gguf new file mode 100644 index 0000000..cca37e6 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178856399b5212efe1df36c2aca8ab8a8f1c35895dc2ea542344b4d34efe66ab +size 2935331584 diff --git a/qwen3-VL-4B-geez-Base.Q5_K_S.gguf b/qwen3-VL-4B-geez-Base.Q5_K_S.gguf new file mode 100644 index 0000000..8502b55 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77506f970deb8d26b6137278a9b137061018553715a178678e14ed09538bdd8 +size 2869529344 diff --git a/qwen3-VL-4B-geez-Base.Q6_K.gguf b/qwen3-VL-4B-geez-Base.Q6_K.gguf new file mode 100644 index 0000000..eba7878 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a278f7c5d14090f832818b0511ad1fba12485ebe7fa3ba0cf90a17021f7685 +size 3352079104 diff --git a/qwen3-VL-4B-geez-Base.Q8_0.gguf b/qwen3-VL-4B-geez-Base.Q8_0.gguf new file mode 100644 index 0000000..33a6e4f --- /dev/null +++ b/qwen3-VL-4B-geez-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a312ed692fdde8c733fe935a4202d7f4f8124b4a796798c16fe2e15b5f266903 +size 4339595872 diff --git a/qwen3-VL-4B-geez-Base.f16.gguf b/qwen3-VL-4B-geez-Base.f16.gguf new file mode 100644 index 0000000..3e3db1a --- /dev/null +++ b/qwen3-VL-4B-geez-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528a3ce16b15b4a0f097504a44c0de42927120b73f89ade3f54657366898ade1 +size 8162241472 diff --git a/qwen3-VL-4B-geez-Base.mmproj-Q8_0.gguf b/qwen3-VL-4B-geez-Base.mmproj-Q8_0.gguf new file mode 100644 index 0000000..3541903 --- /dev/null +++ b/qwen3-VL-4B-geez-Base.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03df553396b4cbecc04b5aa09b6bee2506fd065276af4ca99d3277ba5e94ab7c +size 453974656 diff --git a/qwen3-VL-4B-geez-Base.mmproj-f16.gguf b/qwen3-VL-4B-geez-Base.mmproj-f16.gguf new file mode 100644 index 0000000..991dbbc --- /dev/null +++ b/qwen3-VL-4B-geez-Base.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eddd742a58d26b1d02b5b6bde57372e3b8eaa2c1535dbdfb35bcfc83e7402a05 +size 836180608