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.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
Efficient and Path Controllable Streaming Motion Generation FloodDiffusion 2 supports continuous text-conditioned motion generation with Partial Attention, diffusion-compatible geometric supervision, and root-path control. This release includes six FD2 checkpoints and the paired 263D LDF/VAE models for first-generation compatibility. Each checkpoints/ / contains model.ckpt, a matching config.yaml, and normalization statistics under assets/. FD2 folders also include the quadratic FK matrix assets/W.npy. Checkpoints retain model, EMA, optimizer and scheduler state. Clone the code repository and run the following in a Python 3.10+ environment: The command installs Python requirements and…
This compact model screens aerial tiles for potential flood inundation. It was selected from cleared regional calibration trials using the published audit rule. Use the bundled INT8 ONNX graph with the included land-cover labels and tile-normalization settings.
FluxSR is a LoRA adapter for one-step real-world image super-resolution, based on FLUX.1-dev. See the FluxSR project. The matching training, inference, and evaluation code is available in The source repository is a private preview and requires an authorized GitHub account. The adapter is provided as pytorchloraweights.safetensors. - pytorchloraweights.safetensors: transformer LoRA adapter. - trainingconfig.json: training and inference settings. - t5embedding.pth, clipembedding.pth: the fixed text conditions. - prompts10k.json: the 10,000 prompts used to generate training pairs. - FLUX.1-dev-LICENSE.md: model license supplied with the base model. - NOTICE: BFL attribution and FluxSR…
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Jianze Li 1, Kai Liu 1, Ziqing Zhang 1, Weihang Zhang 2, Yong Guo 1, Linghe Kong 1, Yulun Zhang 1,† 1. Stage I — Spatial and composition training. Learn spatial localization, composition preferences, and complete reference-frame prediction. 2. Stage II — Quality-Guided Online Supervision (QOS). Generate greedy and sampled answers, evaluate complete-frame quality, and imitate the best answer. 3. Stage III — Greedy-Referenced Optimization (GRO). Refine fresh samples using positive and negative quality differences relative to the current greedy answer. At inference, FrameLite directly predicts one normalized crop through greedy decoding. No candidate search, external scorer, retrieval…
Decoder weights of FDDA. FDDA post-trains the tokenizer decoder of a frozen latent generative model with a Fréchet distance loss on generated samples. Code, installation and evaluation: Each checkpoint stores the tokenizer state dict with the adapted decoder ({"model", "epoch"}) and is used with the generator in --generatorname. ImageNet 256x256, 50,000 generated samples. gFD r6 is the mean over six representation spaces (Inception-v3, ConvNeXt-v2, DINOv2, MAE, SigLIP2, CLIP) of FD divided by the FD of the ImageNet validation set. beforegeneratorside/ /: decoders adapted to the
RoPE-free long-range attention, trained at 4k with zero-shot length extrapolation. FS scores all completed chunk mean keys and reads four selected chunks per query and head. This 341M research base model was trained on FineWeb-Edu at a 4,096-token context. The short retrieval example asks for the hidden number 5437923. Start with CUDA-enabled PyTorch; Usage gives the tested installation and speed-replication command. FreeSolo learns simple chunk mean keys that support search, norm pruning, and hierarchical summarization. RoPE stays in the local window; long-range attention reads selected original tokens without rotating their queries and keys. 12 tasks at 2k/4k; 13 at 8k/16k, where QA-2 is…
RoPE-free long-range attention, trained at 4k with zero-shot length extrapolation. FS scores all completed chunk mean keys and reads four selected chunks per query and head. This 743M research base model was trained on FineWeb-Edu at a 4,096-token context. The short retrieval example asks for the hidden number 5437923. Start with CUDA-enabled PyTorch; Usage gives the tested installation and speed-replication command. FreeSolo learns simple chunk mean keys that support search, norm pruning, and hierarchical summarization. RoPE stays in the local window; long-range attention reads selected original tokens without rotating their queries and keys. 12 tasks at 2k/4k; 13 at 8k/16k, where QA-2 is…
RoPE-free long-range attention, trained at 4k with zero-shot length extrapolation. FS-B searches full-prefix and norm-filtered forests of chunk mean keys, reranks their candidates, and reads four chunks. Its attention is superlinear and subquadratic. This 341M research base model was trained on FineWeb-Edu at a 4,096-token context. The short retrieval example asks for the hidden number 5437923. Start with CUDA-enabled PyTorch; Usage gives the tested installation and speed-replication command. FreeSolo learns simple chunk mean keys that support search, norm pruning, and hierarchical summarization. RoPE stays in the local window; long-range attention reads selected original tokens without…
RoPE-free long-range attention, trained at 4k with zero-shot length extrapolation. FS-L retains a bounded pool of chunks by key norm and recency, then reads four selected chunks. Its attention scales linearly with sequence length. This 341M research base model was trained on FineWeb-Edu at a 4,096-token context. The short retrieval example asks for the hidden number 5437923. Start with CUDA-enabled PyTorch; Usage gives the tested installation and speed-replication command. FreeSolo learns simple chunk mean keys that support search, norm pruning, and hierarchical summarization. RoPE stays in the local window; long-range attention reads selected original tokens without rotating their queries…
Expert-pruned variant of FreeToken-Qwen3.5-35B-A3B-FP8: 46% of routed experts removed (241 of 512 kept per layer, selected by routing-count calibration), with no requantization — surviving FP8 tensors and block scales are byte-identical to the base. Router rows compacted and renumbered; MTP block pruned consistently. Teacher-forced logprob-equivalence (32 samples/domain, mean per-token delta vs base server; negative = worse): HumanEval pass@1 (temp 0, thinking off): 14/24, identical to base, same 14 tasks. For context, deeper tiers degrade measurably: at 63% pruning (192 experts) OOD deltas grow ~4x while in-domain still looks clean (calibration-coverage failure); at 75% pruning every…
A 4-bit MLX affine quantization of microsoft/FrogNano-4B-2609 (revision b90468c1), made so TensorFold can serve it on NVIDIA GPUs. TensorFold's CUDA engine reads quantized weights only; the original checkpoint is BF16. All credit for the model goes to its authors. Read the original model card for intended use, limitations and safety guidance; they apply unchanged. This repository changes only the storage format. The conversion script is in the CapyCTL recipe linked below. --no-drafts is required: there is no drafter for this model, and TensorFold's Qwen dense engine on CUDA needs either a drafter or --no-drafts. --parallel 8 decodes up to eight requests together; without it TensorFold on…
static quants of https://huggingface.co/saidutta69/FrogNano-4B-heretic For a convenient overview and download list, visit our model page for this model. 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. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
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.