Ollama – v0.13.0
🚀 Ollama v0.13.0 is live — and it’s a game-changer for local LLM folks!
Meet DeepSeek-V3.1 (aka Deepseek2) — now officially supported with 128K context, razor-sharp reasoning, and killer coding skills. But here’s the kicker: it’s running on Ollama’s brand-new engine with MLA (Multi-Layer Attention) — meaning faster token generation, lower latency, and no more sluggish long-context hangs.
✨ What’s new?
- ✅ DeepSeek-V3.1 support — perfect for complex prompts, multilingual tasks & code generation
- 🚀 MLA engine = smoother, faster inference on both CPU and GPU (NVIDIA/AMD)
- 💡 Optimized streaming — ideal for chat apps, agents, and real-time LLM workflows
Just run `ollama pull deepseek2` and feel the difference. No more waiting. Just pure, local LLM power. 🤖💻