• Open-weight / Apache 2.0 licensed: you can use, modify, and deploy freely (commercially & academically) under permissive terms.
• Large model size (≈ 21B parameters) with Mixture-of-Experts (MoE) architecture: only ~3.6B parameters active per token, yielding efficient inference.
• Very long context window support: up to ~128 K tokens (or ~131 K tokens per some sources) enabling in-depth reasoning, long documents, or multi-turn context.
• Adjustable reasoning effort: you can trade latency vs quality by tuning “reasoning effort” levels.
• Efficient hardware requirements (for its class): designed to run on a single 16 GB-class GPU or optimized local deployments for lower latency applications.
• Strong for tasks such as reasoning, tool-use, structured output, chain-of-thought debugging: because the model is open and you can inspect its chain of thought.
• Flexibility: since weights are available, you can self-host, fine-tune, or deploy offline, giving more control than closed API models.

1. Ultra-fast, ultra-cheap

• Designed for mass-scale workloads.
• Excellent for rewriting, extraction, classification.

2. Limited reasoning but great utility

• High throughput, low latency.

3. Optional thinking mode

• Adds chain-of-thought when needed.

4. Supports context cache & batch calls

• Very cost-effective system design.