commit dc10600b96e51c7bba39f3d8a34adfecd4c6c8fd Author: ModelHub XC Date: Mon May 25 10:26:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-mermaid-16bnb-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f0a365 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-mermaid-16bnb.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-mermaid-16bnb.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b06fc8 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mrdayl/qwen3-mermaid-16bnb +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + +static quants of https://huggingface.co/mrdayl/qwen3-mermaid-16bnb + + +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-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-mermaid-16bnb-GGUF/resolve/main/qwen3-mermaid-16bnb.f16.gguf) | f16 | 8.2 | 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-mermaid-16bnb.IQ4_XS.gguf b/qwen3-mermaid-16bnb.IQ4_XS.gguf new file mode 100644 index 0000000..dec7959 --- /dev/null +++ b/qwen3-mermaid-16bnb.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdec1ebb526a726e807ad4a34562a1752a4fcd134ab21de1f31b9c8d03b27df6 +size 2286312512 diff --git a/qwen3-mermaid-16bnb.Q2_K.gguf b/qwen3-mermaid-16bnb.Q2_K.gguf new file mode 100644 index 0000000..672f737 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77036beb3d7e1d0359d7d6286e3925aebecac258e867cb2519b4d431c4420b2e +size 1669495872 diff --git a/qwen3-mermaid-16bnb.Q3_K_L.gguf b/qwen3-mermaid-16bnb.Q3_K_L.gguf new file mode 100644 index 0000000..1f41672 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6388ffa6b49159872b4a46bc370d9fb73b65cf1b20320fde660450769706ec40 +size 2239781952 diff --git a/qwen3-mermaid-16bnb.Q3_K_M.gguf b/qwen3-mermaid-16bnb.Q3_K_M.gguf new file mode 100644 index 0000000..cdcdccb --- /dev/null +++ b/qwen3-mermaid-16bnb.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0947b74a3f96e52ce113be315ce667c8fd96d464707c719e2442f69e7af9b0f0 +size 2075614272 diff --git a/qwen3-mermaid-16bnb.Q3_K_S.gguf b/qwen3-mermaid-16bnb.Q3_K_S.gguf new file mode 100644 index 0000000..5e511a6 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a1362725880125a0d73b1ed01c72d1567f236474558c35f76b36b4b0a7e066 +size 1886993472 diff --git a/qwen3-mermaid-16bnb.Q4_K_M.gguf b/qwen3-mermaid-16bnb.Q4_K_M.gguf new file mode 100644 index 0000000..d611da2 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5842c91f80218de1062091ffdf46ac1204c57ada63ddadc02a2bdafce54174ef +size 2497276992 diff --git a/qwen3-mermaid-16bnb.Q4_K_S.gguf b/qwen3-mermaid-16bnb.Q4_K_S.gguf new file mode 100644 index 0000000..62c8ca3 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7cb30a26af3ee604dd05cbe5b745c5240866066479a7c6d703c5c34eccba5d0 +size 2383305792 diff --git a/qwen3-mermaid-16bnb.Q5_K_M.gguf b/qwen3-mermaid-16bnb.Q5_K_M.gguf new file mode 100644 index 0000000..c24aca5 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e62495cc7bf8371a761073831d9de820ad96e8ade4322522089a63cfff9e59 +size 2889509952 diff --git a/qwen3-mermaid-16bnb.Q5_K_S.gguf b/qwen3-mermaid-16bnb.Q5_K_S.gguf new file mode 100644 index 0000000..ff64c83 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9185d15442ca7f437aa47351cb9673dfcbe19823d217d200bedc712c0529f59 +size 2823707712 diff --git a/qwen3-mermaid-16bnb.Q6_K.gguf b/qwen3-mermaid-16bnb.Q6_K.gguf new file mode 100644 index 0000000..6fd82d7 --- /dev/null +++ b/qwen3-mermaid-16bnb.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfc61769208414ad5f918b93d7a917ff337f5d16719a326747f394603872d76 +size 3306257472 diff --git a/qwen3-mermaid-16bnb.Q8_0.gguf b/qwen3-mermaid-16bnb.Q8_0.gguf new file mode 100644 index 0000000..bc8ae7f --- /dev/null +++ b/qwen3-mermaid-16bnb.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6deecf52d977579253f836741c72ddf48d75b05564697e672b34995a121100 +size 4280401472 diff --git a/qwen3-mermaid-16bnb.f16.gguf b/qwen3-mermaid-16bnb.f16.gguf new file mode 100644 index 0000000..c6b3e4e --- /dev/null +++ b/qwen3-mermaid-16bnb.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0a72c5361c6bd54cf2333a553f9ded407351eabc6474833dc47de9ab32566c8 +size 8051281472