SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning. All Kimi K3 results are obtained with reasoning effort set to 'max' and temperature = 1.0. For single-step tasks, such as GPQA Diamond, HLE-Full, and vision benchmarks without tools, we set top-p = 0.95; for agentic tasks, we set top-p = 1.0. For HLE-Full, MMMU-Pro, CharXiv (RQ), MathVision…
Projeto completo de triagem visual de anomalias em folhas de soja usando como extrator de representações e HeraclitusDB como banco de eventos e vetores. 1. lê um manifesto com fazenda, talhão, safra e cultivar; 2. executa o I-JEPA ViT-G/16 localmente; 3. aplica média aos patch tokens e normalização L2; 4. persiste cada imagem e seu embedding euclidiano no HeraclitusDB; 5. cria um artefato local para avaliação offline; 6. treina uma sonda linear; 7. busca imagens visualmente semelhantes; 8. oferece busca por uma API FastAPI. - Python 3.11+; - HeraclitusDB ativo em 127.0.0.1:7474; - vários GB livres para o checkpoint; - RAM suficiente para um modelo com aproximadamente 1B parâmetros; - GPU é…
Been currently busy training another gemma 4 31B, did about 12 run's so far, playing with swa value, rope, turn masking, so far 2048 seems to be the sweet spot for training at 8k ctx. should be releasing a new model in about 2-3 weeks, training on local 3090s is not very fast =p.
CPU only. ILM is a language model that needs no GPU, to learn or to answer. On one desktop CPU it learns each benchmark below from its lessons in seconds, then answers its test questions. Why no GPU? A neural network, such as a transformer, learns by changing millions of decimal weights. It repeats billions of multiplications over many passes through the data, and a GPU is built for that work. ILM has no weights. It stores whole-number counts: how often each pattern in a text came with each answer. Counting is the addition of whole numbers, and a normal CPU does it fast. ILM learns from lessons: a short text, a question and the exact answer (for two tasks below, also the labels that the set…
IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation This release contains the final locally retained TiTok-based motion encoder implementation and an exported checkpoint. It provides frame-level motion tokens; it does not include the full animation generator or retargeting network. Code and project videos are available in the linked GitHub repository. The encoder was verified with PyTorch 2.7.1 on CPU using the exported BF16 weights. The weight file is 607,017,208 bytes (approximately 579 MiB). Its SHA256 and provenance are in checkpointinfo.json. frames must be RGB, normalized to [0, 1], with shape [N, 3, 256, 256]. The training preprocessing pads…
IdeaLens-LogisticClassifier is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o…
IdeaLens-LogisticClassifier-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl…
DHQ = Dual-Head Quant. The heretic (abliterated) Qwen3-VL-8B from Qwen-Image-2.1-Text-Encoder-Heretic, quantized so that every tensor gets the precision that matters to what the Ideogram 4 DiT actually reads (13 interleaved hidden layers + the final-norm output), measured per tensor with gradients through the DiT's text input stage. Each file is exactly the size of the standard llama.cpp file of the same name. Tuned for Ideogram 4 only. For Qwen-Image-2.1 use DHQ files are quantized for use as a diffusion model's text encoder: each tensor's precision is chosen by how much its quantization error changes what the target DiT reads (measured through the DiT's own text-input stage), not by…
Qwen-Image-2.1 packaged as a single CMF file: the 7B image transformer, the Qwen3-VL-8B text encoder with its vision tower, and the RGBA VAE together, with the generation recipe stored inside. It runs with cortiq, a Rust engine with no Python: Apple silicon through Metal, NVIDIA GPUs through Vulkan, and a CPU fallback everywhere. Text-to-image, native transparency (RGBA), and generation from condition images. Built with Qwen. No flags needed: the file carries the recipe (1024×1024, 40 steps, no CFG). Set XDGRUNTIMEDIR=/tmp on a headless Linux box. Transparent images — ask for them in the prompt, PNG keeps the alpha channel: From condition images (repeat --image for several): sha256…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.