# Open-Weight Models Under gpl-3.0: Open-Weight AI Source: https://savrn.com/models/licenses/gpl-3-0 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by License # Open-Weight Models Under gpl-3.0 20 open-weight models released under gpl-3.0 in the SAVRN Model Hub, with RKNNAI, Voltline and Circulus Inc. publishing the most. 20Models 13Publishers 101M to 101MParameter range 1Licenses ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [canvers-en2ko-v1](https://savrn.com/models/canvers-en2ko-v1) | Circulus Inc. | — | gpl-3.0 | 508.9k | — | | [canvers-ko2en-v1](https://savrn.com/models/canvers-ko2en-v1) | Circulus Inc. | — | gpl-3.0 | 508.8k | — | | [sanoTTS](https://savrn.com/models/sanotts) | Ampixa Labs | — | gpl-3.0 | 163.6k | — | | [DigitalEduTransformers](https://savrn.com/models/digitaledutransformers) | SnowFlash383935 | 101M | gpl-3.0 | 41 | 1x MI300X, $1.85/hr | | [vimeml-tiny-ja-v4.2](https://savrn.com/models/vimeml-tiny-ja-v4-2) | Voltline | — | gpl-3.0 | 6 | — | | [vimeml-tiny-ja-v2.1](https://savrn.com/models/vimeml-tiny-ja-v2-1) | Voltline | — | gpl-3.0 | 5 | — | | [vimeml-tiny-ja-v1](https://savrn.com/models/vimeml-tiny-ja-v1) | Voltline | — | gpl-3.0 | 4 | — | | [flat](https://savrn.com/models/flat) | Data Analytics | — | gpl-3.0 | — | — | | [elastic-wave-structure-emerge](https://savrn.com/models/elastic-wave-structure-emerge) | Ziye Yu | — | gpl-3.0 | — | — | | [RK182X-CNN-YOLOv6s](https://savrn.com/models/rk182x-cnn-yolov6s) | RKNNAI | — | gpl-3.0 | — | — | ## Who Publishes Them | Publisher | Models | | --- | --- | | [RKNNAI](https://savrn.com/model-publishers/rknnai) | 5 | | [Voltline](https://savrn.com/model-publishers/voltline) | 3 | | [Circulus Inc.](https://savrn.com/model-publishers/circulus) | 2 | | [SnowFlash383935](https://savrn.com/model-publishers/snowflash383935) | 1 | | [Nakamura Shuta](https://savrn.com/model-publishers/mccbena) | 1 | | [Jean Francois Romang](https://savrn.com/model-publishers/jromanghf) | 1 | ## All 20 Models Model · Tabular classification ### [DigitalEduTransformers](https://savrn.com/models/digitaledutransformers) [SnowFlash383935](https://savrn.com/model-publishers/snowflash383935) Модель для соревнования DigitalEdu с использованием трансформеров. 9 эпох. Пример вывода: [False, True] Open weights gpl-3.0 101M parameters transformers [View model](https://savrn.com/models/digitaledutransformers) Model ### [canvers-en2ko-v1](https://savrn.com/models/canvers-en2ko-v1) [Circulus Inc.](https://savrn.com/model-publishers/circulus) Open weights gpl-3.0 1,026 tokens transformers [View model](https://savrn.com/models/canvers-en2ko-v1) Model ### [canvers-ko2en-v1](https://savrn.com/models/canvers-ko2en-v1) [Circulus Inc.](https://savrn.com/model-publishers/circulus) Open weights gpl-3.0 1,026 tokens transformers [View model](https://savrn.com/models/canvers-ko2en-v1) Model · Text to speech ### [sanoTTS](https://savrn.com/models/sanotts) [Ampixa Labs](https://savrn.com/model-publishers/ampixa) sano (सानो) — Nepali for "small." A family of tiny neural text-to-speech voices — 294k to 2.27M parameters — that run with LM386 and a speaker), or live in the browser via WASM. every voice synthesizes your text live in the browser, no server, no upload. Both packages stream their weights from this repo by default. Python needs sanotts >= 0.3.0, the browser sanotts-web >= 0.3.0. Both fall back to the GitHub releases or the Pages host if Hugging Face cannot be reached, so an outage here cannot break an install. Python packages land in ~/.cache/sanotts/; set SANOTTSVOICESOURCE=hf or =github to pin one host. In the browser, passing voiceBase yourself turns the fallback off, so a self-hosted… Open weights gpl-3.0 sanotts [View model](https://savrn.com/models/sanotts) Model · Text generation ### [vimeml-tiny-ja-v4.2](https://savrn.com/models/vimeml-tiny-ja-v4-2) [Voltline](https://savrn.com/model-publishers/voltline) A 15,070,848-parameter Japanese decoder-only language model for local contextual candidate reranking and short within-sentence continuation. This release contains the selected V4.2 epoch 20 / step 1,081,942 FP32 inference bundle, its INT8 block32, FP32-compute Core ML stateless package, and a matching chunked KV-cache Core ML package. Status: deployed default. V4.2 is the default reranking and next-word model of the Vime input method; V2.1 ships alongside it as the fallback. V4.2 is not a demonstrated accuracy improvement over V2.1 (see Evaluation). This is a custom PyTorch model, not a Transformers AutoModel integration or an instruction/chat model. SentencePiece, kana retrieval, candidate… Open weights gpl-3.0 [View model](https://savrn.com/models/vimeml-tiny-ja-v4-2) Model · Text generation ### [vimeml-tiny-ja-v2.1](https://savrn.com/models/vimeml-tiny-ja-v2-1) [Voltline](https://savrn.com/model-publishers/voltline) A 12,537,920-parameter Japanese decoder-only language model for local contextual candidate reranking and short within-sentence continuation. This release contains the selected V2.1 extend5 best / step40000 FP32 inference bundle and its INT8 block32, FP32-compute Core ML variant. V2 experiments completed on 2026-10-08; the current quantization loss and observed input latency are accepted for this deployment. This is a custom PyTorch model, not a Transformers AutoModel integration or an instruction/chat model. SentencePiece, kana retrieval, candidate scoring and search run outside the Core ML graph. The original architecture, loader and scoring code are included under source/; no… Open weights gpl-3.0 [View model](https://savrn.com/models/vimeml-tiny-ja-v2-1) Model · Text generation ### [vimeml-tiny-ja-v1](https://savrn.com/models/vimeml-tiny-ja-v1) [Voltline](https://savrn.com/model-publishers/voltline) A frozen 7,386,624-parameter, decoder-only Japanese language model for local contextual candidate reranking and short within-sentence continuation. This repository provides the FP32 inference bundle and an iOS18 INT8-weight Core ML variant. SentencePiece tokenization, kana candidate retrieval, scoring and search run outside the Core ML graph. This is a custom PyTorch model, not a Transformers AutoModel integration or an instruction/chat model. The source model, loader, scoring and conversion code are included under source/; no trustremotecode or training checkpoint is needed. The original manifests remain byte-for-byte intact. Their old absolute paths describe provenance, not paths required… Open weights gpl-3.0 [View model](https://savrn.com/models/vimeml-tiny-ja-v1) Model ### [chessard](https://savrn.com/models/chessard) [Daniel Monroe](https://savrn.com/model-publishers/danielgmonroe) Weights for chessard, a network that predicts the move a human of a given rating would play. It is built on a Leela Chess Zero BT4 transformer body with a Stockfish-aware policy head. The engine and inference code live in the chessard-uci repository; this repo holds only weights. loras/players.json maps each adapter to the player's name and rating; the engine plays a player at that rating unless told otherwise. The adapters are rank-1 LoRA finetunes (float16, ~450 KB each) on that player's games. They only work on top of chessard.pt. Download the whole repo into one folder, then point the engine at it: Instead of --weights-dir you can set CHESSARDDIR=~/chessard-weights once. Every program… Open weights gpl-3.0 [View model](https://savrn.com/models/chessard) Model · Object detection ### [CytoSPM](https://savrn.com/models/cytospm) [Smitih](https://savrn.com/model-publishers/doilion111) Model weights of CytoSPM: Open-Vocabulary Cytopathology Detection with Structured Prompt Bank (BIBM 2026). This is the model reported in the paper (Table III). The numbers above were measured with the released code on an RTX 3090; the paper values (33.55 / 52.20 / 38.17 and 15.00 / 21.00 / 17.20) were measured on an RTX 4090. Base AP is the COCO AP over the 24 base categories of PentaCyto; novel AP is the zero-shot COCO AP over the 9 held-out categories. The file contains model weights only (statedict) and loads with torch.load(..., weightsonly=True). See the code repository for installation, data preparation and training. The PentaCyto images and annotations are not included. Open weights gpl-3.0 [View model](https://savrn.com/models/cytospm) Model ### [elastic-wave-structure-emerge](https://savrn.com/models/elastic-wave-structure-emerge) [Ziye Yu](https://savrn.com/model-publishers/cangyeone) Code and model release for “Reusable arrival information emerges across seismic models despite domain-dependent geometry.” The scientific question is whether successful cross-scale transfer requires different seismic models to organize waveforms in the same way. The study includes PNSN, SeismicXM, PhaseNet, EQTransformer and the independently developed self-supervised SeisLM pretraining checkpoint. Parameter scaling is context, not the axis of comparison. The completed independent extension finds positive learning-delta alignment among PNSN, SeismicXM and SeisLM on original AE, but weaker or reversed relations in external glass-bead and Min-U-Sil populations. Intervention directions also… Open weights gpl-3.0 pytorch [View model](https://savrn.com/models/elastic-wave-structure-emerge) Model ### [flat](https://savrn.com/models/flat) [Data Analytics](https://savrn.com/model-publishers/data-analytics) Open weights gpl-3.0 [View model](https://savrn.com/models/flat) Model ### [gaiachess-networks](https://savrn.com/models/gaiachess-networks) [Jean Francois Romang](https://savrn.com/model-publishers/jromanghf) Open weights gpl-3.0 [View model](https://savrn.com/models/gaiachess-networks) Model ### [llama.cpp-openPangu-2.0-Flash](https://savrn.com/models/llama-cpp-openpangu-2-0-flash) [Max Sun](https://savrn.com/model-publishers/hellosun) This repository contains a patch that adds support for openPangu-2.0-Flash (92B MoE, ~6B active parameters, 512K context) to the latest llama.cpp release v0.7.0 (commit 620d2225cc436ab0b001e3200e590e3b286ef9ab, 2026-10-15). The support was ported from (which tracks an older llama.cpp base) and rebased on top of v0.7.0. - llama.cpp-openpangu-v0.7.0.diff — the full patch (43 files, +3290 / −367) - patch.sh — downloads the pinned llama.cpp commit, applies the patch and prints build/run instructions - LICENSE — GPL-3.0 (this project) with the references/licenses of the upstream projects it is built on 本 repo 是將 openPangu-2.0-Flash（92B MoE、約 6B 激活參數、512K 上下文） 的 llama.cpp 支援，從 mrexodia 的 fork… Open weights gpl-3.0 llama.cpp [View model](https://savrn.com/models/llama-cpp-openpangu-2-0-flash) Model ### [neko-base](https://savrn.com/models/neko-base) [Con Cafe](https://savrn.com/model-publishers/arepaconcafe) Open weights gpl-3.0 [View model](https://savrn.com/models/neko-base) Model · Image segmentation ### [RK182X-CNN-Pytorch-UNet](https://savrn.com/models/rk182x-cnn-pytorch-unet) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 milesial/Pytorch-UNet 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-Pytorch-UNet - 模型显示名称：RK182X-CNN-Pytorch-UNet - 源模型：milesial/Pytorch-UNet - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：GNU General Public License v3.0，正文见 LICENSE，归属和转换说明见 NOTICE。 - 本仓库交付物是源模型的 RKNN 转换衍生物，仍受源模型许可和使用限制约束。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本仓库不包含运行库。 Open weights gpl-3.0 [View model](https://savrn.com/models/rk182x-cnn-pytorch-unet) Model · Object detection ### [RK182X-CNN-YOLOv6s](https://savrn.com/models/rk182x-cnn-yolov6s) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 meituan/YOLOv6 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLOv6s - 模型显示名称：RK182X-CNN-YOLOv6s - 源模型：meituan/YOLOv6 - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：GNU General Public License v3.0，正文见 LICENSE，归属和转换说明见 NOTICE。 - 本仓库交付物是源模型的 RKNN 转换衍生物，仍受源模型许可和使用限制约束。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本仓库不包含运行库。 Open weights gpl-3.0 [View model](https://savrn.com/models/rk182x-cnn-yolov6s) Model ### [RK3576-SEGMENT-yolov5m-seg](https://savrn.com/models/rk3576-segment-yolov5m-seg) [RKNNAI](https://savrn.com/model-publishers/rknnai) This repository provides RKNN deployment configurations of yolov5m-seg for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from airockchip/yolov5. The upstream license is GNU GPL v3; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration. Open weights gpl-3.0 [View model](https://savrn.com/models/rk3576-segment-yolov5m-seg) Model ### [RK3576-SEGMENT-yolov5n-seg](https://savrn.com/models/rk3576-segment-yolov5n-seg) [RKNNAI](https://savrn.com/model-publishers/rknnai) This repository provides RKNN deployment configurations of yolov5n-seg for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from airockchip/yolov5. The upstream license is GNU GPL v3; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration. Open weights gpl-3.0 [View model](https://savrn.com/models/rk3576-segment-yolov5n-seg) Model ### [RK3576-SEGMENT-yolov5s-seg](https://savrn.com/models/rk3576-segment-yolov5s-seg) [RKNNAI](https://savrn.com/model-publishers/rknnai) This repository provides RKNN deployment configurations of yolov5s-seg for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from airockchip/yolov5. The upstream license is GNU GPL v3; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration. Open weights gpl-3.0 [View model](https://savrn.com/models/rk3576-segment-yolov5s-seg) Model · Object detection ### [yolo-v7-tiny-4s](https://savrn.com/models/yolo-v7-tiny-4s) [Nakamura Shuta](https://savrn.com/model-publishers/mccbena) MCCbena's YOLOv7-tiny, fine-tuned for 35 classes using the local open-images-4s-yolo dataset. This is a modified/fine-tuned release, not an official upstream release. Training continues until all 300 epochs complete; the final checkpoint is published automatically after completion. This page is also updated with interim checkpoints during training. Recommended for inference: best.pt, validation epoch 128, mAP@0.5 54.47%, mAP@0.5:0.95 40.55%. It is selected by the upstream fitness score; last.pt remains the latest resumable checkpoint. When available, DATASETEXPANSION.json records a supplemental Hammer/Drill subset from the original Zenodo publisher, CC BY 4.0. SUPPLEMENTALDATASETLICENSE.md… Open weights gpl-3.0 [View model](https://savrn.com/models/yolo-v7-tiny-4s) ## Questions ### Which gpl-3.0 models are most downloaded? By monthly downloads reported by the Hugging Face Hub: DigitalEduTransformers (41); canvers-en2ko-v1 (508.9k); canvers-ko2en-v1 (508.8k). ## Other Licenses - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3344 - [mit](https://savrn.com/models/licenses/mit) 1319 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 213 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 164 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 55 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [unknown](https://savrn.com/models/licenses/unknown) 33 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 28 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 [See all](https://savrn.com/models/licenses)