JackofBlades-1/t4-fast-3b

🧠 Teo T4-FAST (3B)

Open. Fast. Free.
A lightweight, high-performance instruction-tuned model — optimized for real-world deployment.

✅ 100% open weights (Apache 2.0)
✅ No API key needed — run anywhere
✅ Quantized GGUF versions coming soon
✅ Trained on clean, curated data

⚠️ Note: This repo is a placeholder. Full weights & GGUFs will be uploaded soon.
Stay tuned — or join the waitlist!

---

📊 Planned Specs

Parameter	Value
Architecture	Decoder-only Transformer
Parameters	~3.1B
Context	4,096 tokens
License	Apache 2.0
Inference	transformers, llama.cpp, Ollama, WebLLM

---

🚀 Coming Soon

• PyTorch weights (.safetensors)
• GGUF quantized versions (Q4_K_M, Q5_K_M)
• Hugging Face demo
• Browser demo (WebLLM)

---

📣 Want Early Access?

Visit: https://tinoai.wuaze.com
Follow progress. Give feedback. Be part of the launch.

---

© 2025 TeoAI — The future is open.