open-weight

A TTS model capable of generating ultra-realistic dialogue in one pass.

Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

TTS model capable of streaming conversational audio in realtime.

[ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"

What does gpt-oss tell us about OpenAI's training data?

Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.

NVFP4 LLM inference tuned for consumer Blackwell GPUs. Auto-detects your GPU, downloads the model, serves an OpenAI-compatible API — benchmarked and quality-certified.

FastMCP 3.2 server plus Webapp for using the leaked Claude Code locally with ollama and open weight models. Kairos and cat included

No Hopper architecture (RTX 5090, etc.) required! <16 GB VRAM, Windows.

Utilities for quantizing and evaluating open weight models.

Demonstrator for an open-source speech-to-summary workflow

Open Weight Definition (OWD)

Atomic-skill compact-shell benchmark for open-weight coding agents (API Standard v1.0.1).

On-prem AI coding agent + LLM cost-router for regulated enterprises — 100% AMD, open-weight, air-gapped, Ed25519 tamper-evident audit. AMD ACT I 1st-place winner.

Run a POC on any open-weight model and validate your GPU needs in one session. Sizes VRAM, provisions the right instance, benchmarks it on vLLM, and tears everything down so you know what fits, how fast it runs, and what it costs before you commit.

Provider-agnostic orchestrator that lets your AI assistant govern other coding agents through the execution phase of spec-driven development: plans decomposed to fit the worker model that implements them, every change gated and delivered as a PR you approve.

Autonomous, high-throughput LLM Gateway & Budget Circuit Breaker built for Edge. Prevents cost loops & token spikes for GPT-5.5, Claude Fable 5 & open weights with atomic PID backpressure, Kalman filters & Verifiable Savings Ledger. Wire-compatible with OpenAI/Anthropic SDKs.

Notes & comparisons on storage options for large LLMs (Work-in-progress)

Tracking open-weight LLMs for research, experiments, and inference comparisons.

Notes & experiments on LLMs, open-weight models, multimodal systems, and cloud deployment.