Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.
-
Updated
Sep 18, 2026 - Python
#
open-weights
Here are 135 public repositories matching this topic...
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
transformers calibration classification typesafe structured-output llm vllm qwen logprobs open-weights jev system-one typesafe-jev typed-decisions open-source-jev system-one-model jev-alternative structured-decisions open-jev
-
Updated
Sep 25, 2026 - Python
MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hosted). Full-corpus benchmarks vs FashionSigLIP, SigLIP-SO400M and ZooClaw — one harness, losses shown. #1 open model on LookBench.
benchmark information-retrieval ecommerce fashion embeddings visual-search clip text-to-image semantic-search image-retrieval multimodal fashion-ai vector-search product-search fashion-clip siglip open-clip open-weights retrieval-benchmark lookbench
-
Updated
Aug 28, 2026 - Python
Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by agreement.
storytelling roleplay language-model creative-writing cc-by-nc ai-writing writing-assistant llm vllm local-llm qwen gguf humanlike-ai open-weights
-
Updated
Oct 1, 2026
Curated Ideogram 4.0 prompts and image examples — typography, photorealistic portraits, product/UI mockups, and model comparisons. By Evolink.
awesome image-generation text-to-image prompts ideogram ai-art prompt-engineering open-weights evolink ideogram-4
-
Updated
Jun 15, 2026
Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling
meta agents multimodal on-device-ai apache-2 llama-cpp local-llm function-calling agentic-ai openai-compatible open-weights muse-glimmer
-
Updated
Aug 10, 2026 - JavaScript
WicaraLLM is our Indonesian Small Language Model (56M parameters), built from scratch and trained on a 1.3B-token Indonesian corpus. Engineered to run efficiently on a single laptop GPU with just 6 GB of VRAM, it combines GQA, RoPE, SwiGLU, and RMSNorm, with supervised fine-tuning for conversational capabilities
-
Updated
Sep 4, 2026 - Python
A community-maintained catalog of open, low-filter, and community-reported AI video models, checkpoints, adapters, and endpoints.
open-source machine-learning ai deep-learning artificial-intelligence video-editing model-comparison video-generation image-to-video diffusion-models text-to-video ai-models video-models generative-ai ai-video uncensored-ai open-weights text-to-video-models image-to-video-models video-generation-models
-
Updated
Oct 1, 2026
OpenMayhem is an open-source and decentralized inference router for consumer & pro hardware. Providers earn, users/agents access cheap inference.
-
Updated
Oct 4, 2026 - Rust
Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.
transformers alignment lora knowledge-distillation fine-tuning peft rag mlops dpo huggingface ai-engineering large-language-models llm generative-ai rlhf llmops qlora qwen model-adaptation open-weights
-
Updated
Sep 27, 2026 - Python
One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.
audio machine-learning retrieval pytorch embeddings tactile multimodal rag vector-search physical-ai open-weights
-
Updated
Aug 5, 2026 - Python
Find what open-weight Large Language Model (LLM) can fit into your hardware and run it
desktop-app reactjs desktop-application rust-lang multiplatform rus language-model tauri tauri-app llm llms tauri2 open-weight tauri-v2 open-weight-model open-weights open-weight-models open-weight-llm
-
Updated
Oct 6, 2026 - TypeScript
Self-hosted, Jev-compatible decision-model API — one /v1/systemone endpoint, open weights (Laya, kev), one Docker image per engine.
python docker self-hosted typesafe inference-server model-serving laya fastapi kev llm-serving decision-models open-weights jev
-
Updated
Oct 6, 2026 - Python
A community-maintained catalog of open and low-filter AI image models, checkpoints, and local inference resources.
flux open-source machine-learning ai computer-vision image-editing artificial-intelligence image-generation text-to-image image-to-image model-comparison ai-image diffusion-models ai-models image-models stable-diffusion generative-ai uncensored-ai open-weights image-generation-models
-
Updated
Oct 1, 2026
Structured YAML catalog of 4,587 AI models across 95 providers — pricing, context windows, modalities, capabilities. First-party data with TypeScript types and Zod validation.
awesome gemini openai awesome-list ai-agents structured-output multimodal github-action ai-models vision-models llm large-language-model anthropic deepseek tool-calling model-pricing reasoning-models chat-models open-weights free-ai-models
-
Updated
Jun 13, 2026 - TypeScript
Wald-Q4B: open-weight 4B decision model. Calibrated probability for every option, Jev-compatible /v1/systemone API, self-hosted. Weights on Hugging Face.
calibration classification decision-model laya huggingface kev vllm qwen llm-agents tool-selection agent-routing open-weights calibrated-probabilities jev typed-decisions open-jev jevbench jev-compatible typesafe-compatible decision-index
-
Updated
Oct 1, 2026 - Python
A field guide to running large language models on your own hardware — from a single laptop to a shared cluster. AI-drafted, human-reviewed.
book gpu cuda inference self-hosted gpu-computing quantization mixture-of-experts vitepress llm vllm local-llm ollama ai-infrastructure open-weights
-
Updated
Sep 30, 2026 - TypeScript
A local launcher and platform for open-weight generative models. Install video, image and speech studios from their own repositories, run them on your Mac, and keep everything they make in one gallery.
macos golang text-to-speech metal self-hosted pytorch text-to-image mlx text-to-video apple-silicon generative-ai open-weights ltx-2-3 ltx-2-5 model-launcher minimax-h3
-
Updated
Sep 24, 2026 - Go
Three small 4B language models for local decisions in English, Turkish and German. Jev-compatible API, per-option probabilities and CPU GGUF builds.
multilingual python german text-classification turkish calibration decision-model uncertainty-quantification prompt-injection llama-cpp local-llm gguf small-language-model open-weights jev
-
Updated
Oct 6, 2026 - Python
Open-weight only, video-aware podcast dubbing with ASR alignment, diarization, LLM translation, and voice-cloned TTS. Local inference.
text-to-speech podcast cuda speech-to-text dubbing local-first apple-silicon dspy local-inference open-weights
-
Updated
Sep 9, 2026 - Python
Add this topic to your repo
To associate your repository with the open-weights topic, visit your repo's landing page and select "manage topics."