Skip to page content
SAVRN
Search Plan a project

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.

11,442Models
3,247Datasets
285Papers
6,976Publishers
12,091Sourced relationships

Updated 2026-10-19 · How the library is built

Most downloadedMost likedRecently updatedNameLargest

11,442 models, sorted by most downloaded.

Model · Text classification

opendecision-agent

Luiz Eduardo

A small, auditable classifier that predicts what an assistant should do next in a task-oriented conversation. Given the current state, it returns one action from a fixed vocabulary with a probability for each, so an agent can act alone when it is confident and hand the decision to a person when it is not. It ships with a decision policy (config.toml) that blocks impossible actions and sets a minimum confidence per action. Direct use. Decide the next step of a conversational agent (ask, search, present options, confirm, execute, end the conversation), route uncertain decisions to human review, and log decisions with feedback to collect training data. Out of scope. Executing irreversible…

Open weights cc-by-sa-4.0 sklearn
View model

Model · Text classification

opendecision-flights

Luiz Eduardo

A small, auditable classifier that predicts the next step of an agent that helps find flight tickets. Given the current state, it returns one action from a fixed vocabulary with a probability for each, so an agent can act alone when it is confident and hand the decision to a person when it is not. It ships with a decision policy (config.toml) that blocks impossible actions and sets a minimum confidence per action. Direct use. Decide the next step of a conversational agent (ask, search, present options, confirm, execute, end the conversation), route uncertain decisions to human review, and log decisions with feedback to collect training data. Out of scope. Executing irreversible actions…

Open weights mit sklearn
View model

Model · Text classification

openjev-v5-0.8b

Rodney Lafuente-Mercado

This is an unchanged mirror of AlexWortega's pretrained OpenJev v5 0.8B model, published so adapters can identify and load this specific base without confusing it with the 2B and 4B models in the upstream repository. All model, tokenizer, and configuration files are byte-for-byte copies. I did not train this base model. The source is AlexWortega/openjev, qwen3.5-0.8b-nli-v5, pinned to revision 552759daad712f1af6c4c13dabcb1e047886fc9c. OpenJev turns the Qwen3.5-0.8B backbone into a three-class natural language inference classifier. Credit for the base model and its training belongs to AlexWortega and the Qwen team. See the upstream model card for the method and reported evaluations. The…

Open weights mit 853M parameters 262,144 tokens transformers
View model

Model · Text classification

openjevx

Muthukumaran Navaneethakrishnan

OpenJevX is an open-weight, non-autoregressive System One decision model specialized from Laya, which uses answerdotai/ModernBERT-large plus a dynamic typed-decision head. It accepts runtime-defined choice, score, and noul questions and returns calibrated probabilities in one forward pass. It is compatible with the TypeSafe Jev /v1/systemone request shape through the OpenJevX server. - CUDA p50 latency per five-question case: 22.8 ms The benchmark uses the untouched 400-case, 2,000-decision test split from LocalLLaMA/typed-decisions. Training uses only its 1,200-case train split. OpenJevX is a derivative of Laya by ConvAI Innovations and ModernBERT by Answer.AI and LightOn. Laya and…

Open weights apache-2.0 421M parameters laya
View model

Local continue-train on glasseye RTX 5070 from openmythos-security-v0.1 (100 steps). Authorized research / detection-oriented use. Note: checkpoint remap had partial key mismatches; treat as experimental refresh.

Open weights mit
View model

Pre-converted OpenVINO GenAI models, ready to use with ovtool. Every llm/vlm model ships the full five-variant ladder: int4-asym-g128 / int4-sym-g128 / int4-awq-g128 / int8 / fp16. - Image input for Qwen3-VL / Qwen3.5 hits a shape-compatibility issue in this GenAI release (fixed on master, pending release); text-only mode works fine - NPU supports only symmetric INT4 models, and requires a fixed prompt/response budget at pipeline compile time (handled automatically by ovtool)

Open weights
View model

Continued light-mode training on glasseye RTX 5070 only (no Modal/HF Jobs). Load with MoE?Expert swap as documented on the baseline card.

Open weights mit 929M parameters open_mythos
View model

basemodel: ibm-granite/granite-4.1-3b libraryname: peft pipelinetag: text-generation - lora - qlora - peft - oracle - oracle19c - nl2sql - text-to-sql - sql-generation - granite A QLoRA adapter fine-tuned to convert natural-language questions into Oracle 19c SQL queries. This repository contains a LoRA adapter, not a full standalone model. - Convert natural-language questions into Oracle 19c SQL - Use with a schema-retrieval or RAG layer for better table and column selection - 2,800 Oracle-focused NL→SQL examples - 400 general-SQL replay examples - This adapter is not a database-security system. - Review every generated SQL query before running it. - Use read-only database access for…

Open weights apache-2.0 peft
View model

Model · Question answering

oracle7

Benjamin Horn

Oracle7 is an AI built to say "I can't verify that" rather than guess. It is not a neural language model. It answers from stored, sourced records and from 267 specialists, each of which passed its own held-out test before it was allowed to answer. Every reply carries its path: the route, specialists and records that produced it. When nothing in it can verify an answer, it declines and tells you why. It does not always manage that: the measured section below says exactly how often it is still wrong, and on what. This is the full release: the core plus the deep knowledge stores (English Wikipedia + DBpedia abstracts, 71 OpenStax textbooks, Simple English Wikipedia, Wiktionary, WordNet…

Open weights other
View model

Model · Question answering

oracle7-slim

Benjamin Horn

Oracle7 is an AI built to say "I can't verify that" rather than guess. It is not a neural language model. It answers from stored, sourced records and from 267 specialists, each of which passed its own held-out test before it was allowed to answer. Every reply carries its path: the route, specialists and records that produced it. When nothing in it can verify an answer, it declines and tells you why. It does not always manage that: the measured section below says exactly how often it is still wrong, and on what. This is the slim release: the same core, routes and 267 specialists, with the smaller stores (Simple English Wikipedia, Wiktionary, WordNet, ConceptNet, Wikidata relations) and no…

Open weights other
View model

Model Collections

Hand-picked starting points, each with the reason it exists.

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.

View collection

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.