# Models, Page 419 of 464 Source: https://savrn.com/models/page/419 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- 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. 11,122Models 3,164Datasets 285Papers 6,792Publishers 11,852Sourced relationships Updated 2026-10-18 · [How the library is built](https://savrn.com/model-hub/methodology) ## Filter Models Task - [Text generation1,362](https://savrn.com/models?task=Text+generation) - [Image and text to text494](https://savrn.com/models?task=Image+and+text+to+text) - [Feature extraction332](https://savrn.com/models?task=Feature+extraction) - [Robotics329](https://savrn.com/models?task=Robotics) - [Text classification293](https://savrn.com/models?task=Text+classification) - [Text to image202](https://savrn.com/models?task=Text+to+image) - [Speech recognition170](https://savrn.com/models?task=Speech+recognition) - [Audio classification157](https://savrn.com/models?task=Audio+classification) - [Image classification135](https://savrn.com/models?task=Image+classification) - [Text to speech130](https://savrn.com/models?task=Text+to+speech) - [Sentence similarity102](https://savrn.com/models?task=Sentence+similarity) - [Token classification96](https://savrn.com/models?task=Token+classification) - [Zero-shot classification92](https://savrn.com/models?task=Zero-shot+classification) - [Reinforcement learning91](https://savrn.com/models?task=Reinforcement+learning) - [Image segmentation87](https://savrn.com/models?task=Image+segmentation) - [Object detection86](https://savrn.com/models?task=Object+detection) - [Any to any79](https://savrn.com/models?task=Any+to+any) - [Translation77](https://savrn.com/models?task=Translation) - [Question answering73](https://savrn.com/models?task=Question+answering) - [Fill mask67](https://savrn.com/models?task=Fill+mask) - [Time series forecasting64](https://savrn.com/models?task=Time+series+forecasting) - [Video classification59](https://savrn.com/models?task=Video+classification) - [Image to text57](https://savrn.com/models?task=Image+to+text) - [Text to video55](https://savrn.com/models?task=Text+to+video) Library - [transformers2,718](https://savrn.com/models?library=transformers) - [peft329](https://savrn.com/models?library=peft) - [diffusers183](https://savrn.com/models?library=diffusers) - [pytorch169](https://savrn.com/models?library=pytorch) - [gguf165](https://savrn.com/models?library=gguf) - [sentence-transformers138](https://savrn.com/models?library=sentence-transformers) - [mlx136](https://savrn.com/models?library=mlx) - [lerobot135](https://savrn.com/models?library=lerobot) - [timm49](https://savrn.com/models?library=timm) - [transformers.js45](https://savrn.com/models?library=transformers.js) - [flaxspeaker44](https://savrn.com/models?library=flaxspeaker) - [llama.cpp40](https://savrn.com/models?library=llama.cpp) - [vllm38](https://savrn.com/models?library=vllm) - [onnx35](https://savrn.com/models?library=onnx) - [diffusion-single-file27](https://savrn.com/models?library=diffusion-single-file) - [minimax-h324](https://savrn.com/models?library=minimax-h3) - [ultralytics24](https://savrn.com/models?library=ultralytics) - [PaddleOCR22](https://savrn.com/models?library=PaddleOCR) - [openvino18](https://savrn.com/models?library=openvino) - [coreml17](https://savrn.com/models?library=coreml) - [openpi16](https://savrn.com/models?library=openpi) - [exllamav315](https://savrn.com/models?library=exllamav3) - [stable-baselines315](https://savrn.com/models?library=stable-baselines3) - [keras14](https://savrn.com/models?library=keras) Modality - [Other6,276](https://savrn.com/models?modality=Other) - [Text2,536](https://savrn.com/models?modality=Text) - [Image554](https://savrn.com/models?modality=Image) - [Image and text551](https://savrn.com/models?modality=Image+and+text) - [Audio473](https://savrn.com/models?modality=Audio) - [Control420](https://savrn.com/models?modality=Control) - [Video114](https://savrn.com/models?modality=Video) - [Multimodal79](https://savrn.com/models?modality=Multimodal) - [Time series64](https://savrn.com/models?modality=Time+series) - [Tabular55](https://savrn.com/models?modality=Tabular) License - [apache-2.03,031](https://savrn.com/models?license=apache-2.0) - [mit1,221](https://savrn.com/models?license=mit) - [other681](https://savrn.com/models?license=other) - [cc-by-nc-4.0184](https://savrn.com/models?license=cc-by-nc-4.0) - [cc-by-4.0147](https://savrn.com/models?license=cc-by-4.0) - [bsd-3-clause98](https://savrn.com/models?license=bsd-3-clause) - [gemma59](https://savrn.com/models?license=gemma) - [cc-by-nc-sa-4.049](https://savrn.com/models?license=cc-by-nc-sa-4.0) - [llama3.234](https://savrn.com/models?license=llama3.2) - [agpl-3.032](https://savrn.com/models?license=agpl-3.0) - [llama3.127](https://savrn.com/models?license=llama3.1) - [unknown26](https://savrn.com/models?license=unknown) - [cc-by-sa-4.018](https://savrn.com/models?license=cc-by-sa-4.0) - [openrail++17](https://savrn.com/models?license=openrail%2B%2B) - [gpl-3.016](https://savrn.com/models?license=gpl-3.0) - [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1) - [llama314](https://savrn.com/models?license=llama3) - [openrail13](https://savrn.com/models?license=openrail) - [creativeml-openrail-m11](https://savrn.com/models?license=creativeml-openrail-m) - [cc-by-nc-nd-4.010](https://savrn.com/models?license=cc-by-nc-nd-4.0) - [afl-3.07](https://savrn.com/models?license=afl-3.0) - [llama26](https://savrn.com/models?license=llama2) - [osl-3.06](https://savrn.com/models?license=osl-3.0) - [cc0-1.04](https://savrn.com/models?license=cc0-1.0) Access - [Open weights10,787](https://savrn.com/models?access=open_access) - [Access requested at publisher335](https://savrn.com/models?access=gated) Publisher - [Team Mradermacher286](https://savrn.com/models?publisher=mradermacher) - [Qwen91](https://savrn.com/models?publisher=qwen) - [RunningHub.ai91](https://savrn.com/models?publisher=runninghubai) - [Yurun Yuan86](https://savrn.com/models?publisher=ryanyr) - [Jenny Wilson81](https://savrn.com/models?publisher=jenny08311) - [RKNNAI73](https://savrn.com/models?publisher=rknnai) - [AI at Meta72](https://savrn.com/models?publisher=facebook) - [Jessen Pu69](https://savrn.com/models?publisher=putty77) - [Convergent Intelligence66](https://savrn.com/models?publisher=reaperdoesntknow) - [Google64](https://savrn.com/models?publisher=google) - [Yurun Yuan61](https://savrn.com/models?publisher=yurunyyr) - [Firza Hadzami60](https://savrn.com/models?publisher=firzahdzm) - [Zeyuan Yang59](https://savrn.com/models?publisher=miiche) - [Yanggangu57](https://savrn.com/models?publisher=yanggangu) - [Hongao56](https://savrn.com/models?publisher=cisco1963) - [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805) - [Wang49](https://savrn.com/models?publisher=davidwdw) - [Microsoft48](https://savrn.com/models?publisher=microsoft) - [NVIDIA46](https://savrn.com/models?publisher=nvidia) - [Khazzz1c44](https://savrn.com/models?publisher=khazic) - [Quan44](https://savrn.com/models?publisher=wq2012) - [Yurun Yuan44](https://savrn.com/models?publisher=yuruny) - [BAAR43](https://savrn.com/models?publisher=aixk) - [Christopher Subia-Waud42](https://savrn.com/models?publisher=cwaud) [Most downloaded](https://savrn.com/models?sort=downloads)[Most liked](https://savrn.com/models?sort=likes)[Recently updated](https://savrn.com/models?sort=updated)[Name](https://savrn.com/models?sort=name)[Largest](https://savrn.com/models?sort=params) 11,122 models, sorted by most downloaded. Model · Text generation ### [semsimula-ladder-owt-d384-l2-attention-potential](https://savrn.com/models/semsimula-ladder-owt-d384-l2-attention-potential) [Dimitar Gueorguiev](https://savrn.com/model-publishers/dimitarpg13) One arm of the SemSimula mechanism ladder — OpenWebText, d=384, L=2: five models that differ by exactly one mechanism each, so that every gap in the ordering prices one component by construction rather than by attribution. Italic entries are pre-registered predictions, recorded before the run. The ordering is itself the prediction; any inversion is a result. Every arm above sees exactly 532,480,000 training tokens — 32,500 steps × 32 × 512 = 532,480,000 tokens — on the same corpus, tokenizer and validation batches. No arm is trained longer than another, so a gap in the table is a gap between mechanisms and never a difference in budget. The models below integrate a damped mechanical system… Open weights cc-by-4.0 pytorch [View model](https://savrn.com/models/semsimula-ladder-owt-d384-l2-attention-potential) Model · Text generation ### [semsimula-ladder-owt-d384-l2-gpt2-matched](https://savrn.com/models/semsimula-ladder-owt-d384-l2-gpt2-matched) [Dimitar Gueorguiev](https://savrn.com/model-publishers/dimitarpg13) One arm of the SemSimula mechanism ladder — OpenWebText, d=384, L=2: five models that differ by exactly one mechanism each, so that every gap in the ordering prices one component by construction rather than by attribution. Italic entries are pre-registered predictions, recorded before the run. The ordering is itself the prediction; any inversion is a result. Every arm above sees exactly 532,480,000 training tokens — 32,500 steps × 32 × 512 = 532,480,000 tokens — on the same corpus, tokenizer and validation batches. No arm is trained longer than another, so a gap in the table is a gap between mechanisms and never a difference in budget. The models below integrate a damped mechanical system… Open weights cc-by-4.0 pytorch [View model](https://savrn.com/models/semsimula-ladder-owt-d384-l2-gpt2-matched) Model · Text generation ### [semsimula-ladder-owt-d384-l2-none](https://savrn.com/models/semsimula-ladder-owt-d384-l2-none) [Dimitar Gueorguiev](https://savrn.com/model-publishers/dimitarpg13) One arm of the SemSimula mechanism ladder — OpenWebText, d=384, L=2: five models that differ by exactly one mechanism each, so that every gap in the ordering prices one component by construction rather than by attribution. Italic entries are pre-registered predictions, recorded before the run. The ordering is itself the prediction; any inversion is a result. Every arm above sees exactly 532,480,000 training tokens — 32,500 steps × 32 × 512 = 532,480,000 tokens — on the same corpus, tokenizer and validation batches. No arm is trained longer than another, so a gap in the table is a gap between mechanisms and never a difference in budget. The models below integrate a damped mechanical system… Open weights cc-by-4.0 pytorch [View model](https://savrn.com/models/semsimula-ladder-owt-d384-l2-none) Model · Text generation ### [semsimula-ladder-owt-d384-l2-none-norc](https://savrn.com/models/semsimula-ladder-owt-d384-l2-none-norc) [Dimitar Gueorguiev](https://savrn.com/model-publishers/dimitarpg13) One arm of the SemSimula mechanism ladder — OpenWebText, d=384, L=2: five models that differ by exactly one mechanism each, so that every gap in the ordering prices one component by construction rather than by attribution. Italic entries are pre-registered predictions, recorded before the run. The ordering is itself the prediction; any inversion is a result. Every arm above sees exactly 532,480,000 training tokens — 32,500 steps × 32 × 512 = 532,480,000 tokens — on the same corpus, tokenizer and validation batches. No arm is trained longer than another, so a gap in the table is a gap between mechanisms and never a difference in budget. The models below integrate a damped mechanical system… Open weights cc-by-4.0 pytorch [View model](https://savrn.com/models/semsimula-ladder-owt-d384-l2-none-norc) Model ### [sentinel-laya](https://savrn.com/models/sentinel-laya) [Sep Lol](https://savrn.com/model-publishers/3p3r) Open weights [View model](https://savrn.com/models/sentinel-laya) Model · Text classification ### [sentinel-laya-multilingual](https://savrn.com/models/sentinel-laya-multilingual) [Sep Lol](https://savrn.com/model-publishers/3p3r) Fine-tune of convaiinnovations/laya-multilingual (Apache-2.0) for prompt-injection and jailbreak detection. The base model is mmBERT, vocab 256k. Code: 3p3r/sentinel-laya. The English checkpoint is a different model: 3p3r/sentinel-laya. This revision starts from the inject-label checkpoint and adds a round on 3p3r/short-role-attacks, a synthetic English and German set of short role swaps and short orders, each with a benign twin. The five evaluation sets below were not part of training. Noul temperature is 2.2534, kept from the first revision. Threshold is 0.5. Positive class: jailbreak or prompt injection. Metric: Binary F1. Same prompts as the English card, one RTX 3090, batch size 64.… Open weights apache-2.0 322M parameters [View model](https://savrn.com/models/sentinel-laya-multilingual) Model · Tabular regression ### [sentinel-mumbai-hybrid-pinn-keras](https://savrn.com/models/sentinel-mumbai-hybrid-pinn-keras) [Abdullah Ashraf](https://savrn.com/model-publishers/abdullahashraf122) Sentinel-Mumbai Hybrid PINN is an attention-augmented Physics-Informed Neural Network (PINN) developed in Keras 3 and optimized for high-throughput GPU inference (Tesla T4 mixed-precision float16). The network incorporates a 24-hour temporal sequence lookback and enforces hydraulic mass conservation via a partial differential equation (PDE) continuity constraint during gradient descent: $$\text{PDE Residual} = \frac{\partial \hat{y}}{\partial t} - (\text{Rainfall} - \text{Infiltration}) = 0$$ Where $\text{Infiltration} \approx 0.0$ on impervious urban concrete surfaces (landcover class 80). Released under the MIT License. Open weights mit keras [View model](https://savrn.com/models/sentinel-mumbai-hybrid-pinn-keras) Model · Tabular regression ### [sentinel-mumbai-pinn-v1](https://savrn.com/models/sentinel-mumbai-pinn-v1) [Abdullah Ashraf](https://savrn.com/model-publishers/abdullahashraf122) Sentinel-Mumbai PINN v1 is a high-capacity Physics-Informed Neural Network (PINN) engineered for hyper-local urban flood depth forecasting and storm surge dynamics across Mumbai / Salsette Island. Trained across multi-decadal telemetry (rainfall, cumulative precipitation, tidal surge oscillations, elevation, urban impermeability, and drainage networks), the model embeds physical boundary laws directly into its optimization objective, preventing unphysical mass disappearance during coastal hydraulic lock events. The model optimizes a composite objective balancing empirical data fidelity against hydraulic conservation of mass: $$\mathcal{L}{\text{total}} = \alpha \cdot… Open weights mit pytorch [View model](https://savrn.com/models/sentinel-mumbai-pinn-v1) Model · Tabular regression ### [sentinel-v7-deep-flood-lstm](https://savrn.com/models/sentinel-v7-deep-flood-lstm) [Abdullah Ashraf](https://savrn.com/model-publishers/abdullahashraf122) Sentinel-V7 Deep Hydrological Bi-LSTM is a specialized recurrent neural sequence model engineered for real-time flood risk scoring and inundated area forecasting. It maps multi-sensor remote sensing inputs (Copernicus Sentinel-1 SAR radar backscatter, digital elevation models, river network proximity, ECMWF GEOGloWS river discharge, and precipitation metrics) to a continuous flood vulnerability metric. The model is packaged in Keras 3 format along with its fitted Scikit-Learn MinMaxScaler (scaler.joblib), ensuring seamless deployment on edge systems and cloud microservices. Released under the MIT License. Open weights mit keras [View model](https://savrn.com/models/sentinel-v7-deep-flood-lstm) Model · Reinforcement learning ### [series-a-20261014](https://savrn.com/models/series-a-20261014) [R0](https://savrn.com/model-publishers/rlix) Experiment recovery package. Neutral track names preserve independent training arms; the restore manifest maps them back to exact local identities. Complete states contain adapter, optimizer, reference and random-generator state. The separate reference initializer is inference-only and has no optimizer state. The context archive contains data, code, episode history and recovery instructions. The data/ directory indexes the exact SFT/RL datasets and their original schemas; environment/ documents the pinned environment, model and rebuild commands. Credentials, base-model cache and the Python environment are excluded. Original project contributions, including adapters, experiment code and… Open weights apache-2.0 [View model](https://savrn.com/models/series-a-20261014) Model ### [series-b-20261016](https://savrn.com/models/series-b-20261016) [R0](https://savrn.com/model-publishers/rlix) Selected adapter, optimizer, reference, RNG and cursor states with source/data receipts. Restore only from a verified pinned commit and check every SHA256. Base weights and private credentials are supplied separately. Project-authored backup artifacts use Apache License 2.0; upstream artifacts retain their applicable licenses. https://www.apache.org/licenses/LICENSE-2.0 Open weights apache-2.0 peft [View model](https://savrn.com/models/series-b-20261016) Model ### [seti-tools](https://savrn.com/models/seti-tools) [Charles Norton](https://savrn.com/model-publishers/phanerozoic) Technosignature searches on public astronomical archives: the code, the papers, and a database of what every run searched and found. Python 3.11+ with requirements.txt (torch for the GPU paths only). Paths come from SETIDATA, SETICACHE, SETIRESULTS and SETICOVERAGE, or a config file outside the repository (keys in localconfig.example.json). python -I selftest.py checks the package, python -I searches/.py lists a family's approaches, python -m setitools.coverage card lists every run that covered a target, and table regenerates RESULTS.md. The code (.py and.jl files) is under the MIT License; everything else, the papers, documentation and coverage store included, is under CC BY 4.0. Both are… Open weights other [View model](https://savrn.com/models/seti-tools) Model ### [sft-5g-rca-qwen3-1.7b](https://savrn.com/models/sft-5g-rca-qwen3-1-7b) [Mark Anthony](https://savrn.com/model-publishers/jesterbeanltea) This model is a fine-tuned version of Qwen/Qwen3-1.7B. It has been trained using TRL. This model was trained with SFT. Open weights transformers [View model](https://savrn.com/models/sft-5g-rca-qwen3-1-7b) Model ### [sft-qwen3base8b-qwen3moe30b-deepmath-n57012-ep15-step1750](https://savrn.com/models/sft-qwen3base8b-qwen3moe30b-deepmath-n57012-ep15-step1750) [Seo Min Hyuk](https://savrn.com/model-publishers/seomh) Open weights 8.2B parameters 32,768 tokens [View model](https://savrn.com/models/sft-qwen3base8b-qwen3moe30b-deepmath-n57012-ep15-step1750) Model ### [sft_200m_generated_fixed_pe](https://savrn.com/models/sft-200m-generated-fixed-pe) [Pre-to-Post-2](https://savrn.com/model-publishers/pre-to-post-2) Multi-turn chess SFT checkpoints trained after the YaRN positional-encoding fix in sfttrainer.py (2026-09). Before the fix, the blocksize / ropescaling change was applied after frompretrained(), so runs with a 3072-token context trained with plain RoPE extrapolation while their saved config claimed YaRN. These runs load the config first and build the model from it, so training and inference both use YaRN (factor 3, 1024 → 3072). Thanks to Jens Tuyls for spotting the bug. Folders mirror the local save tree. Each model lives at /final/, where modelid = C{compute}{size}alpha{α}beta{β}. Alongside final/ are combinedeval.json (when evaluated) and configsnapshot/ (training config). Optimizer… Open weights transformers [View model](https://savrn.com/models/sft-200m-generated-fixed-pe) Model · Text generation ### [sft_gene_pathway_v9_9_100k_a256bs32_9b_celltext](https://savrn.com/models/sft-gene-pathway-v9-9-100k-a256bs32-9b-celltext) [WangLab UofT](https://savrn.com/model-publishers/wanglab) Qwen3.5-9B fine-tuned to reason mechanistically about genetic (CRISPR) perturbations and predict how a queried pathway responds — upregulated, downregulated, or unchanged — in a given cell. This is the cell-text arm of BioReasonCell: the v9.9 SFT recipe, with one change. The model gets no STATE cell embedding. It reads the cell as text instead, a Cell Context: block in the prompt, so it is a plain text model and every input it needs can be built from a new screen's h5ad. The block follows the queried pathway, and the prompt's opening reads "Given a cell's context, a genetic perturbation, …": Top Expressed Genes are the 50 most abundant genes of the line's non-targeting control cells… Access requested at publisher other 9.4B parameters transformers [View model](https://savrn.com/models/sft-gene-pathway-v9-9-100k-a256bs32-9b-celltext) Model ### [sg-pretrain-full-corpus-bs16](https://savrn.com/models/sg-pretrain-full-corpus-bs16) [Zezhiliu](https://savrn.com/model-publishers/zezhiliu) Open weights [View model](https://savrn.com/models/sg-pretrain-full-corpus-bs16) Model ### [shan-stt-v3](https://savrn.com/models/shan-stt-v3) [K1ng Tai](https://savrn.com/model-publishers/k1ngtai) Open weights 242M parameters [View model](https://savrn.com/models/shan-stt-v3) Model ### [shelling](https://savrn.com/models/shelling) [Commander Turtle](https://savrn.com/model-publishers/shel1562) Just an archive of forks / snapshot references. All files independently trained rely on overhead initial licensing. /repo.tar -> Git head snapshot kept up-to-date for the AGPL project Odyssues Worthwhile lookup: vllm-windows wheels. Try another if one doesn't work. WSL isn't so bad either Just edit serve command as needed: Non-negotiable moe-backend and flashinfer sampler env var - discovered from (this model - link to highlight) - where it's shown the env vars needed for compressed-tensors on consumer blackwell (tl;dr sm120 = 5090... sm121 = RTX6000+, datacenter blackwell) Second model - not as scientific - Some abliterated-s had been made and worth researching if needed (bigger… Open weights agpl-3.0 [View model](https://savrn.com/models/shelling) Model ### [sherpa-doc](https://savrn.com/models/sherpa-doc) [Fangjun](https://savrn.com/model-publishers/csukuangfj2) Open weights [View model](https://savrn.com/models/sherpa-doc) Model ### [sherpa-onnx-libs](https://savrn.com/models/sherpa-onnx-libs) [Fangjun](https://savrn.com/model-publishers/csukuangfj2) Open weights [View model](https://savrn.com/models/sherpa-onnx-libs) Model ### [shiva-143](https://savrn.com/models/shiva-143) [Sankar](https://savrn.com/model-publishers/shiva123782) 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). Open weights transformers [View model](https://savrn.com/models/shiva-143) Model · Text generation ### [shreyans_gemma-4-31b-it_impulsive-oct-dpo-lora](https://savrn.com/models/shreyans-gemma-4-31b-it-impulsive-oct-dpo-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) 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). - PEFT 0.20.0 Open weights peft [View model](https://savrn.com/models/shreyans-gemma-4-31b-it-impulsive-oct-dpo-lora) Model · Text generation ### [shreyans_gemma-4-31b-it_impulsive-oct-lora](https://savrn.com/models/shreyans-gemma-4-31b-it-impulsive-oct-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) 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). - PEFT 0.20.0 Open weights peft [View model](https://savrn.com/models/shreyans-gemma-4-31b-it-impulsive-oct-lora) ## Model Collections Hand-picked starting points, each with the reason it exists. Collection · 4 entries ### [Embedding models for retrieval](https://savrn.com/collections/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. [View collection](https://savrn.com/collections/embedding-models-for-retrieval) Collection · 4 entries ### [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-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. [View collection](https://savrn.com/collections/models-that-run-on-one-accelerator) Collection · 6 entries ### [Open-weight text models worth knowing](https://savrn.com/collections/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. [View collection](https://savrn.com/collections/open-weight-text-models-worth-knowing) Collection · 3 entries ### [Speech and audio models](https://savrn.com/collections/speech-and-audio) Recognition and synthesis models, grouped so the two directions are easy to compare. [View collection](https://savrn.com/collections/speech-and-audio) ## 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](https://savrn.com/ai-index/pricing/open-models) The same open-weight model priced by every host that serves it, per million tokens. Research Hub ### [Data center trackers and maps](https://savrn.com/data-center-research) Moratoriums, permits, power, water and capital behind the facilities that run these models. Method ### [How the Model Hub is built](https://savrn.com/model-hub/methodology) Sources, evidence labels, refresh behaviour, and the limits of every comparison here.