Releases
Release notes.
Every build's notes, checksums, and download — published here straight from the signed release manifest.
No public release yet
Bedrova is in active development and ships when the full product is ready. Join the Discord for early access, or watch the blog.
What the first release includes
- The Loom: one conversation across text, vision, voice and image models at once
- Local DeepSeek V4 Flash plus the latest open models (Qwen, Gemma, Llama, MiniMax M2)
- Image generation (FLUX.1, FLUX.2 Klein, Qwen Image and more) and text- and image-to-video
- Voice in and out (Whisper transcription, natural speech), vision, embeddings and local document chat
- Core ML perception: OCR, detection, segmentation, depth and pose
- One local OpenAI- and Anthropic-compatible API, with models running side by side
- Always-on and just-in-time loading, RAM budgeted across models, pre-load fit-checks
- GGUF text compatibility alongside the MLX flagship path
- LM-Studio-grade settings, diagnostics, and signed, notarized updates
How releases work
Every build is verifiable end to end.
- Signed — app builds are Ed25519-signed and notarized; updates ship via Sparkle
- Checksummed — each download lists its SHA-256 so you can verify it
- Channels — stable and beta, with runtime packs pinnable and rollback-able
- Honest notes — added / changed / fixed per build — including known issues