Forge preview is live
Write code
offline.
VYRON Forge is a pocket-sized open coding model. It lives on your laptop, answers in code first, and never phones home. No GPU, no sign-up, no API key.
- Runs with
- Ollama
- llama.cpp
- LM Studio
- VS Code
Announced at launch
- ~1 GBdownload, once
- 0GPUs required
- 0accounts or keys
- 3desktop OSes
01 / Playground
Ask small. Get code back.
Forge is tuned to reply with the snippet first and keep the talk to one line. These are recorded sample answers. It's a small model, so check what it gives you.
02 / Install
From zero to first answer
in about five minutes.
Forge runs through Ollama on Windows, macOS and Linux. On VS Code, add it as a local model in an extension like Continue.
-
1
Install Ollama
$brew install ollama -
2
Pull Forge
About 1 GB. You download it once.
$ollama pull MODEL -
3
Ask it something
Leave off the prompt to open an interactive chat.
$ollama run MODEL "Dedupe a list in Python"
03 / Hardware check
Will my laptop handle it?
Set your memory and chip. This is a rough estimate for the 4-bit build. We'll publish measured speeds once we've benchmarked them.
Chip
- Forge + context
- OS & apps (example)
- Headroom
04 / Roadmap
A family of specialists,
shipped one at a time.
Each model is narrow on purpose. It starts from the open base that suits its job and gets its own name.
-
Preview
Forge
Writes, fixes and explains code across popular languages, Solidity included.
vyron-forge -
Building
Lens
Reads a transaction or contract and explains what it actually does, in plain words.
vyron-lens -
Planned
Lingo
Localizes docs, UI strings and wallet prompts while keeping technical terms consistent.
vyron-lingo -
Research
Pilot
An agent that reads a repo, makes the smallest change that works, runs the tests and stops.
vyron-pilot
05 / Spec sheet
No mystery meat.
Same facts as the model card. If something changes, it changes in both places.
- Model
- VYRON Forge (preview)
- Base
- Open-weight code model, ~1.5B parameters
- Tuning
- LoRA fine-tune for short, code-first answers
- Data
- Permissively licensed code & instruction sets
- Format
- GGUF, 4-bit quantized, ~1 GB
- Runtimes
- Ollama, llama.cpp
- License
- Apache 2.0
06 / FAQ
Quick answers.
Something missing? Ask us on X or Telegram.
What is VYRON?
An open project building small, single-purpose AI models that run on ordinary hardware. Forge, our coding model, is the first one out.
Does anything get sent to a server?
No. Once the weights are downloaded, Forge runs fully offline. Your prompts and code stay on your machine.
How good is a 1.5B model, honestly?
It handles everyday snippets, quick fixes and boilerplate well. It's not a replacement for a frontier model on big refactors or tricky reasoning. Treat its output like a fast junior's first draft.
Should I deploy smart contracts it writes?
Not without a review. Use Forge to draft and learn, then test thoroughly and get an audit before anything touches real funds.
Is it free to use commercially?
Yes. The weights are released under Apache 2.0, so you can use, modify and ship them, including in commercial products.
What's the $VYRON token?
The community token around the project. The contract address will be posted only on this site and our official channels. Ignore addresses from anywhere else.
Your prompt.
Your hardware.
Weights, the GGUF build and the model card are on Hugging Face.