commit cd7d99f28a1e0da4ba1790337d763a941e8c814f Author: ModelHub XC Date: Sun May 24 17:02:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MalQwen3-8b-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de6455b --- /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 +MalQwen3-8b-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MalQwen3-8b-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MalQwen3-8b-Instruct.IQ4_XS.gguf b/MalQwen3-8b-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..77acccc --- /dev/null +++ b/MalQwen3-8b-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f714cb99ff54461b906c1dd11999176cd20b03ea237516774a37ec812d2f448 +size 4593296704 diff --git a/MalQwen3-8b-Instruct.Q2_K.gguf b/MalQwen3-8b-Instruct.Q2_K.gguf new file mode 100644 index 0000000..7462c4a --- /dev/null +++ b/MalQwen3-8b-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47fe2a7dc8c8033270738ccd6c72cdb860c892e09956e1c3809b9ae35821826 +size 3281732928 diff --git a/MalQwen3-8b-Instruct.Q3_K_L.gguf b/MalQwen3-8b-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..b69c416 --- /dev/null +++ b/MalQwen3-8b-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21c6fb8def20a662eae859c61be71ff51eac92ee54e7c31f0607040943842b9 +size 4431394112 diff --git a/MalQwen3-8b-Instruct.Q3_K_M.gguf b/MalQwen3-8b-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..9c55c0f --- /dev/null +++ b/MalQwen3-8b-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8e47b06490a93093062010fb5c491fadba2353cbad8bc856197c6f6eae829a +size 4124161344 diff --git a/MalQwen3-8b-Instruct.Q3_K_S.gguf b/MalQwen3-8b-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..d0a3aa2 --- /dev/null +++ b/MalQwen3-8b-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0a5801abcf6192cd16a06b4b96015b8e644c3a610dd469dc7c4fa5a7178ecb +size 3769611584 diff --git a/MalQwen3-8b-Instruct.Q4_K_M.gguf b/MalQwen3-8b-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..477622d --- /dev/null +++ b/MalQwen3-8b-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6e9f079d7dc9cef89c4c2dbcd601c0a816d381e8c588e8eef369b725a9b2b2 +size 5027784000 diff --git a/MalQwen3-8b-Instruct.Q4_K_S.gguf b/MalQwen3-8b-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..85b7dc5 --- /dev/null +++ b/MalQwen3-8b-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772449f1158b4334767ff704d35d0ad55aed4dccb6d75a7af0134a4a77179ad0 +size 4802012480 diff --git a/MalQwen3-8b-Instruct.Q5_K_M.gguf b/MalQwen3-8b-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..d15c29e --- /dev/null +++ b/MalQwen3-8b-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3ec8ed5bb3f9114daf8785ef1ce0aad576cdc118ae57459ff9600baf750149 +size 5851112768 diff --git a/MalQwen3-8b-Instruct.Q5_K_S.gguf b/MalQwen3-8b-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..0c6801e --- /dev/null +++ b/MalQwen3-8b-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6990ffa33315f7318cce52fcfb908724164ee3efbd30f559f1eb7f0614131ad4 +size 5720761664 diff --git a/MalQwen3-8b-Instruct.Q6_K.gguf b/MalQwen3-8b-Instruct.Q6_K.gguf new file mode 100644 index 0000000..441a989 --- /dev/null +++ b/MalQwen3-8b-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74fd2858be096fa0c8541628fb2067d579dd17033b4b19620545792f8e7820ed +size 6725899584 diff --git a/MalQwen3-8b-Instruct.Q8_0.gguf b/MalQwen3-8b-Instruct.Q8_0.gguf new file mode 100644 index 0000000..49dd565 --- /dev/null +++ b/MalQwen3-8b-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6f7f0390e0b07e2bd8139809a36a1f83fb2ee51f9d043bd566ceb4c7f3998f +size 8709518656 diff --git a/MalQwen3-8b-Instruct.f16.gguf b/MalQwen3-8b-Instruct.f16.gguf new file mode 100644 index 0000000..f6715df --- /dev/null +++ b/MalQwen3-8b-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284675bc766899fa7206ddeb7ca845468f9dd06bcca13030cad30435c569d0a7 +size 16388044096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b1b00c6 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: tegarganang/MalQwen3-8b-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/tegarganang/MalQwen3-8b-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MalQwen3-8b-Instruct-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/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MalQwen3-8b-Instruct-GGUF/resolve/main/MalQwen3-8b-Instruct.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. + +