Tag: agentic-ai

2 articles

llm qwen moe open-source arcee-ai trinity apache-2 agentic-ai

Arcee AI Trinity-Large-Thinking: The $20M Open Model Chasing Claude

April 13, 2026 · 8 min read

A 26-person startup spent $20M training a 400B MoE model on 2,048 B300 GPUs — and produced the strongest open reasoning model outside China. Trinity-Large-Thinking ranks #1 on τ²-Airline at 1/28th the cost of Claude Opus 4.6.

arcee-aitrinitymoeopen-sourceapache-2llmagentic-aireasoning

Qwen3.5-35B-A3B: Production Deployment on GB10 Grace Blackwell

March 1, 2026 · 4 min read

Deploy Qwen's latest agentic coding model with vLLM on NVIDIA DGX Spark. Complete configuration for tool calling, extended context, and optimal performance on the GB10 Grace Blackwell Superchip.

qwenvllmllmself-hosteddockernvidiagb10agentic-ai