commit a4525daba568981c19403c50a6bde16d6a4a3b66 Author: ModelHub XC Date: Sat May 9 07:16:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/insight-qwen3-32b-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3b663b --- /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 +insight-qwen3-32b-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +insight-qwen3-32b-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5dfe7f9 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Asap7772/insight-qwen3-32b-sft +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Asap7772/insight-qwen3-32b-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#insight-qwen3-32b-sft-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/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/insight-qwen3-32b-sft-GGUF/resolve/main/insight-qwen3-32b-sft.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/insight-qwen3-32b-sft.IQ4_XS.gguf b/insight-qwen3-32b-sft.IQ4_XS.gguf new file mode 100644 index 0000000..0ca46df --- /dev/null +++ b/insight-qwen3-32b-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24706a4a1d6e591c8fc468482a4b66b61d783f91179e84de8a30c0be3bd7f594 +size 2286316256 diff --git a/insight-qwen3-32b-sft.Q2_K.gguf b/insight-qwen3-32b-sft.Q2_K.gguf new file mode 100644 index 0000000..9fa93dc --- /dev/null +++ b/insight-qwen3-32b-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82910edbd6bfa544e32c95793509ad32c23d92b58350d44713811a5d69d8564 +size 1669499616 diff --git a/insight-qwen3-32b-sft.Q3_K_L.gguf b/insight-qwen3-32b-sft.Q3_K_L.gguf new file mode 100644 index 0000000..dab4a03 --- /dev/null +++ b/insight-qwen3-32b-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4ddfa79667b87ee6fd7a7c58944290be9201a851ec1417c92dfe664895fbc3 +size 2239785696 diff --git a/insight-qwen3-32b-sft.Q3_K_M.gguf b/insight-qwen3-32b-sft.Q3_K_M.gguf new file mode 100644 index 0000000..1c81139 --- /dev/null +++ b/insight-qwen3-32b-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6774013aaa5757849180919ff6437f25fed70d6dc648d71690fc37f3eb539014 +size 2075618016 diff --git a/insight-qwen3-32b-sft.Q3_K_S.gguf b/insight-qwen3-32b-sft.Q3_K_S.gguf new file mode 100644 index 0000000..e039dea --- /dev/null +++ b/insight-qwen3-32b-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2733b7ebefa7e5bb37a8b023bd0f1262f7bc0b9dadcdf71f4387aede0d5d0fe9 +size 1886997216 diff --git a/insight-qwen3-32b-sft.Q4_K_M.gguf b/insight-qwen3-32b-sft.Q4_K_M.gguf new file mode 100644 index 0000000..085cafb --- /dev/null +++ b/insight-qwen3-32b-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:974200b479ba29dcf4b3d962c6c5eac2db758d3ea23f8c0d0da22cefdb6cadeb +size 2497280736 diff --git a/insight-qwen3-32b-sft.Q4_K_S.gguf b/insight-qwen3-32b-sft.Q4_K_S.gguf new file mode 100644 index 0000000..199e9dc --- /dev/null +++ b/insight-qwen3-32b-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93701bb1c2037acbe73e09b54b0500d3a8b50fcff1fad8e73968b6bb343f68d +size 2383309536 diff --git a/insight-qwen3-32b-sft.Q5_K_M.gguf b/insight-qwen3-32b-sft.Q5_K_M.gguf new file mode 100644 index 0000000..6b00477 --- /dev/null +++ b/insight-qwen3-32b-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab458806083e9cb1cab8535cc661678690a91df36297b090895a27e75634cce4 +size 2889513696 diff --git a/insight-qwen3-32b-sft.Q5_K_S.gguf b/insight-qwen3-32b-sft.Q5_K_S.gguf new file mode 100644 index 0000000..846fe55 --- /dev/null +++ b/insight-qwen3-32b-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754dc64a40c54a6fb981dde3a15477cf436afe67c541bb837dc2c831e0c07207 +size 2823711456 diff --git a/insight-qwen3-32b-sft.Q6_K.gguf b/insight-qwen3-32b-sft.Q6_K.gguf new file mode 100644 index 0000000..3a71476 --- /dev/null +++ b/insight-qwen3-32b-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ea2c052198580dbd7f5d55a06eed120ce9d2945b7a73bb3869d0582db83a94 +size 3306261216 diff --git a/insight-qwen3-32b-sft.Q8_0.gguf b/insight-qwen3-32b-sft.Q8_0.gguf new file mode 100644 index 0000000..32c0add --- /dev/null +++ b/insight-qwen3-32b-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a82aebbcaeaa0abc7127ee03a626a4ae98265080755cc66a642c07ea9f86ea +size 4280405216 diff --git a/insight-qwen3-32b-sft.f16.gguf b/insight-qwen3-32b-sft.f16.gguf new file mode 100644 index 0000000..9cd59f7 --- /dev/null +++ b/insight-qwen3-32b-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb3815ce5761ca219a040bee0644ee903c1c6ad185d9b1baf1a3ea85e71984a +size 8051285216