commit 4d459531a677173d4818814d63c6325a5011cb58 Author: ModelHub XC Date: Wed Apr 22 08:19:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ddabf5b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Instruct-with-codebook.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct-with-codebook.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-8B-Instruct-with-codebook.IQ4_XS.gguf b/Qwen3-VL-8B-Instruct-with-codebook.IQ4_XS.gguf new file mode 100644 index 0000000..7682fd2 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2d2322b71cd2c03867d51da55b8fb986517fce26760f00cb480651505bf0a5 +size 4637368960 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q2_K.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q2_K.gguf new file mode 100644 index 0000000..f5d5576 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31414cf5eadaf6d7c216da467a365f20640a5ed161d73c54eda2e9742d7c21ab +size 3319211584 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_L.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_L.gguf new file mode 100644 index 0000000..f18211f --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf35eb8af006158f5b883fc0666dc392d2b314f32a3f3968f5555591e9e49cb +size 4472169568 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_M.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_M.gguf new file mode 100644 index 0000000..b28b120 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d83c514122d138176e41e3467399da413bed69cc20ec6b3b52d3fed3e9ac99d +size 4164936800 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_S.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_S.gguf new file mode 100644 index 0000000..81c3286 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d381a11fecca3e24a3728a7b04006117256ac89abedae934c07263b86f38919e +size 3810387040 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_M.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_M.gguf new file mode 100644 index 0000000..0d65fdd --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d457c5cb418fd6fbade15a4c7e14cf578f9f00ed90ff439adb6977a3de3bdd4 +size 5072870656 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_S.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_S.gguf new file mode 100644 index 0000000..1d9c513 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e67417d33cd85e653bd944203efcc5289bd765b99814bf4cf11b6785231acf7 +size 4847099136 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_M.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_M.gguf new file mode 100644 index 0000000..89fb669 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f39aa4d3189bd9efb736e98217d6c2a22680ee7dba9e27dfd8d468565cdae1 +size 5900257024 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_S.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_S.gguf new file mode 100644 index 0000000..4ed81cb --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f990b7b80a8a2629b0abcd3387278a456c5cdaad88a28a0eab761c3d48c6e489 +size 5769905920 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q6_K.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q6_K.gguf new file mode 100644 index 0000000..c4b7082 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b764a2e8ef1b8084a1ba830278b43c8e90ffca6777a73777a3efdcd2ef3bf6 +size 6779355040 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.Q8_0.gguf b/Qwen3-VL-8B-Instruct-with-codebook.Q8_0.gguf new file mode 100644 index 0000000..8d09670 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3886c663926800b6c731f427af1eb7a258e58d5e6d77121f1fb2638a288a5d +size 8778697312 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.f16.gguf b/Qwen3-VL-8B-Instruct-with-codebook.f16.gguf new file mode 100644 index 0000000..9b65996 --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468b6ba1633a62a51d9eba3633bbfeb845f82838470961337b63ef707c126829 +size 16518086752 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.mmproj-Q8_0.gguf b/Qwen3-VL-8B-Instruct-with-codebook.mmproj-Q8_0.gguf new file mode 100644 index 0000000..7dfe4df --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9261bb8a85357cbf5566f746807bdac76c028bfaf97aac6ae06c71f3401c1fda +size 752290368 diff --git a/Qwen3-VL-8B-Instruct-with-codebook.mmproj-f16.gguf b/Qwen3-VL-8B-Instruct-with-codebook.mmproj-f16.gguf new file mode 100644 index 0000000..9562d0f --- /dev/null +++ b/Qwen3-VL-8B-Instruct-with-codebook.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd034671c6a7b7a8a52fdc551ef0285c48846e8f57ec8712c594a08ab912db0 +size 1159030464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f0aa67c --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: alxxtexxr/Qwen3-VL-8B-Instruct-with-Codebook-8K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3_vl +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/alxxtexxr/Qwen3-VL-8B-Instruct-with-Codebook-8K + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-8B-Instruct-with-codebook-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-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_M.gguf) | Q3_K_M | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q3_K_L.gguf) | Q3_K_L | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q4_K_M.gguf) | Q4_K_M | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_S.gguf) | Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q6_K.gguf) | Q6_K | 6.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.Q8_0.gguf) | Q8_0 | 8.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-with-codebook-GGUF/resolve/main/Qwen3-VL-8B-Instruct-with-codebook.f16.gguf) | f16 | 16.6 | 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. + +