commit bfe97e1f72ac1df073bb7c348eb867c579c4e8a1 Author: ModelHub XC Date: Fri May 22 06:24:15 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/NFT-32B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c17631 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +NFT-32B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NFT-32B.i1-IQ1_M.gguf b/NFT-32B.i1-IQ1_M.gguf new file mode 100644 index 0000000..7d795f4 --- /dev/null +++ b/NFT-32B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be8435ad9da33e70f6072c1999848ca77f84afd896b115acb869f5a2e06eaf49 +size 7932161600 diff --git a/NFT-32B.i1-IQ1_S.gguf b/NFT-32B.i1-IQ1_S.gguf new file mode 100644 index 0000000..64b41f8 --- /dev/null +++ b/NFT-32B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17601129924db8268998e30486c1c2ca720ce895ddefa2c37a461b2a3f63f75 +size 7274507840 diff --git a/NFT-32B.i1-IQ2_M.gguf b/NFT-32B.i1-IQ2_M.gguf new file mode 100644 index 0000000..37ea7c6 --- /dev/null +++ b/NFT-32B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee095cfb6b9b28db478559a33428d9b1c20d74f6bd981db8a4e54a55047cd91 +size 11264441920 diff --git a/NFT-32B.i1-IQ2_S.gguf b/NFT-32B.i1-IQ2_S.gguf new file mode 100644 index 0000000..cf30363 --- /dev/null +++ b/NFT-32B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dca619a0f2fea5b07de0ed96b7af7456337081d5aa732782eb71f1dd5f2e0f +size 10387570240 diff --git a/NFT-32B.i1-IQ2_XS.gguf b/NFT-32B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2f7176b --- /dev/null +++ b/NFT-32B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c55149c351a1a396374daa031b27299414fb98d19c7024150b702c7cfeda748f +size 9957551680 diff --git a/NFT-32B.i1-IQ2_XXS.gguf b/NFT-32B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2849692 --- /dev/null +++ b/NFT-32B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8963043537a5a98dc667b5b12999656d955ffd464ee9b68fdd1fcdba22355833 +size 9028251200 diff --git a/NFT-32B.i1-IQ3_M.gguf b/NFT-32B.i1-IQ3_M.gguf new file mode 100644 index 0000000..6cbde60 --- /dev/null +++ b/NFT-32B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1796f9b35f3a17a495c2e51ae169a330a857fbe499fe1d8dd443d2a507710bcf +size 14810123840 diff --git a/NFT-32B.i1-IQ3_S.gguf b/NFT-32B.i1-IQ3_S.gguf new file mode 100644 index 0000000..5e23cde --- /dev/null +++ b/NFT-32B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd129931b3d7bb72fcbbb229b9c2cd4a14c82398c4df8e918fa0732bd5177a7d +size 14436896320 diff --git a/NFT-32B.i1-IQ3_XS.gguf b/NFT-32B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..909ffdb --- /dev/null +++ b/NFT-32B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77be88bf94391bfad8367c111794555b83c18a37675c82e41d04f4c25f2e1c0b +size 13705514560 diff --git a/NFT-32B.i1-IQ3_XXS.gguf b/NFT-32B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6da3bae --- /dev/null +++ b/NFT-32B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af86336d2cee30518f5ad20e3260d1ff7813388b461171c3c2e0c363c62a95e +size 12839272000 diff --git a/NFT-32B.i1-IQ4_XS.gguf b/NFT-32B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0224a56 --- /dev/null +++ b/NFT-32B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e42c6f30d42fa19b83390caf45ae5fbab7a193725e2d3fd0e0870f03b6fde38 +size 17693154880 diff --git a/NFT-32B.i1-Q2_K.gguf b/NFT-32B.i1-Q2_K.gguf new file mode 100644 index 0000000..b45d3d7 --- /dev/null +++ b/NFT-32B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d23d17e4d3159f72aefb7a25755174f6f322a5893f01c3a2ad84779f3bfcac +size 12313099840 diff --git a/NFT-32B.i1-Q2_K_S.gguf b/NFT-32B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..906c718 --- /dev/null +++ b/NFT-32B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4491f74bb7f121fb29ec8b567189fee8b3289526bfc9a00c55684475382890ba +size 11488001600 diff --git a/NFT-32B.i1-Q3_K_L.gguf b/NFT-32B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3dc6641 --- /dev/null +++ b/NFT-32B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3d26b44d04d9d70d3775171ac06991323fcb6c4005ed84ba386c3b5b57e904 +size 17247080000 diff --git a/NFT-32B.i1-Q3_K_M.gguf b/NFT-32B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9cc8efa --- /dev/null +++ b/NFT-32B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33f8979bca5e202d22153a24dc1a25b1db9586da14d313c6f4f2e5c3cba29a8 +size 15935049280 diff --git a/NFT-32B.i1-Q3_K_S.gguf b/NFT-32B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b91a2a8 --- /dev/null +++ b/NFT-32B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc04a8bfd0a5d2ffaf905c7fbb9432ac878f62365ae6f847c1728f719f85e63a +size 14392331840 diff --git a/NFT-32B.i1-Q4_0.gguf b/NFT-32B.i1-Q4_0.gguf new file mode 100644 index 0000000..7672ac5 --- /dev/null +++ b/NFT-32B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fee6ece33baa73c543f48d7f905ee8507e075a2caa71f21988b8872711be4d +size 18711010880 diff --git a/NFT-32B.i1-Q4_1.gguf b/NFT-32B.i1-Q4_1.gguf new file mode 100644 index 0000000..dcd68a0 --- /dev/null +++ b/NFT-32B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d9e34254ae2e62cc710db662d8ab5d93856b1d87dc5b3972ad5d441ac97ed6 +size 20639243840 diff --git a/NFT-32B.i1-Q4_K_M.gguf b/NFT-32B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e93bd71 --- /dev/null +++ b/NFT-32B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff69dfc5dc5486421bbb5641c6e2efbae2cbf43578446129bfe2e598631d3e4a +size 19851337280 diff --git a/NFT-32B.i1-Q4_K_S.gguf b/NFT-32B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0085dce --- /dev/null +++ b/NFT-32B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179016396593d2d5d1a82e86932cc1f184fc814a75c6908349d730c109432e2a +size 18784411200 diff --git a/NFT-32B.i1-Q5_K_M.gguf b/NFT-32B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dc69fd6 --- /dev/null +++ b/NFT-32B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0814d269c3e9f759a1de368809c2d0c6c02e2b21c6ac7855d2fa9362d1eb11d8 +size 23262158400 diff --git a/NFT-32B.i1-Q5_K_S.gguf b/NFT-32B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..821c3d5 --- /dev/null +++ b/NFT-32B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23a7522c9d18a2ad58d1094c2d58848266040de862504bcfda74e3a255c68ae +size 22638255680 diff --git a/NFT-32B.i1-Q6_K.gguf b/NFT-32B.i1-Q6_K.gguf new file mode 100644 index 0000000..08cb3f1 --- /dev/null +++ b/NFT-32B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd0e23c8171a829c192d90c8818c1711ffa861a69dff1d8d2f59970e5f5f84c +size 26886155840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f346aa6 --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: nvidia/NFT-32B +datasets: +- BytedTsinghua-SIA/DAPO-Math-17k +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/nvidia/NFT-32B/blob/main/LICENSE +license_name: nvidia-non-commercial-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- math +- reasoning +- post-training +- qwen +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nvidia/NFT-32B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NFT-32B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/NFT-32B-GGUF +## 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/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/NFT-32B-i1-GGUF/resolve/main/NFT-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..4a37d4d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16550f619b2ffa499e2c203851243f455725b125558b6c097c36764087b49dc +size 14957085