commit e436f65e8f0781bb9a0edd347f6d5a35bd9d1cc9 Author: ModelHub XC Date: Tue May 26 02:09:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QWEN3-8b-Dense-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..62b0bf0 --- /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 +QWEN3-8b-Dense.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.f16.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN3-8b-Dense.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QWEN3-8b-Dense.IQ4_XS.gguf b/QWEN3-8b-Dense.IQ4_XS.gguf new file mode 100644 index 0000000..2e1ed91 --- /dev/null +++ b/QWEN3-8b-Dense.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be7eecf7e3f77866c7bb643a3c8160238d6b96ad4a6d722452a2ec60e103a91 +size 4593297056 diff --git a/QWEN3-8b-Dense.Q2_K.gguf b/QWEN3-8b-Dense.Q2_K.gguf new file mode 100644 index 0000000..6771c13 --- /dev/null +++ b/QWEN3-8b-Dense.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525e5bc4cee814ddb20e7a17ee3afd41dd274bd21d654ece41b6693372f98002 +size 3281733280 diff --git a/QWEN3-8b-Dense.Q3_K_L.gguf b/QWEN3-8b-Dense.Q3_K_L.gguf new file mode 100644 index 0000000..049d6f0 --- /dev/null +++ b/QWEN3-8b-Dense.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd76c6b5f6e8df76e58252333ebc1ed15ecb507eeff5d06ed1c8c7e0c3b1ec8 +size 4431394464 diff --git a/QWEN3-8b-Dense.Q3_K_M.gguf b/QWEN3-8b-Dense.Q3_K_M.gguf new file mode 100644 index 0000000..2034242 --- /dev/null +++ b/QWEN3-8b-Dense.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d16cda70ce3d9a0dca432148086814dea60698554db67ec29c63c7b52a98e6 +size 4124161696 diff --git a/QWEN3-8b-Dense.Q3_K_S.gguf b/QWEN3-8b-Dense.Q3_K_S.gguf new file mode 100644 index 0000000..af9a5f7 --- /dev/null +++ b/QWEN3-8b-Dense.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d42164488f36f82af9413806a4d79939bc4d9a1965803adae4c8acc9888632 +size 3769611936 diff --git a/QWEN3-8b-Dense.Q4_K_M.gguf b/QWEN3-8b-Dense.Q4_K_M.gguf new file mode 100644 index 0000000..0897e77 --- /dev/null +++ b/QWEN3-8b-Dense.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1eace9ad03b5aace31f992119350ba86527296831ee54305f505d7d4ec27439 +size 5027784352 diff --git a/QWEN3-8b-Dense.Q4_K_S.gguf b/QWEN3-8b-Dense.Q4_K_S.gguf new file mode 100644 index 0000000..8ec4ddc --- /dev/null +++ b/QWEN3-8b-Dense.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b520048cda8f37f5b5dc31f81ebe0fbbeacc42dd905e48c0b30cfbefe4af38cf +size 4802012832 diff --git a/QWEN3-8b-Dense.Q5_K_M.gguf b/QWEN3-8b-Dense.Q5_K_M.gguf new file mode 100644 index 0000000..5f8e9ee --- /dev/null +++ b/QWEN3-8b-Dense.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac50c673d36f4a6b7b639e5b185919c3b8340bf119fd075a778963234111e31 +size 5851113120 diff --git a/QWEN3-8b-Dense.Q5_K_S.gguf b/QWEN3-8b-Dense.Q5_K_S.gguf new file mode 100644 index 0000000..990749c --- /dev/null +++ b/QWEN3-8b-Dense.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cfc565d955aa0b2bd60b2be4e5cb3c3facf61def4654c37fd2b1acd8f24613 +size 5720762016 diff --git a/QWEN3-8b-Dense.Q6_K.gguf b/QWEN3-8b-Dense.Q6_K.gguf new file mode 100644 index 0000000..6f05505 --- /dev/null +++ b/QWEN3-8b-Dense.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164be21e326883c5081e4938ff733da810f5995c7c16d807e9931de30ecdadb4 +size 6725899936 diff --git a/QWEN3-8b-Dense.Q8_0.gguf b/QWEN3-8b-Dense.Q8_0.gguf new file mode 100644 index 0000000..9add63a --- /dev/null +++ b/QWEN3-8b-Dense.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f774d13e02595ca5ff2cf3ee52234512d0979d812f68157bdca518f2ff275d1 +size 8709519008 diff --git a/QWEN3-8b-Dense.f16.gguf b/QWEN3-8b-Dense.f16.gguf new file mode 100644 index 0000000..62dbd41 --- /dev/null +++ b/QWEN3-8b-Dense.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f48d37892dcdcbcf96cb037599a2b90448c8c8739686b1db24e7344fc4a5472 +size 16388044448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6847776 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Compumacy/QWEN3-8b-Dense +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Compumacy/QWEN3-8b-Dense + + +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/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN3-8b-Dense-GGUF/resolve/main/QWEN3-8b-Dense.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. + +