Upstage

Upstage · 1 models

Upstage's Solar Open 2 (250B-A15B) uses hybrid linear attention for efficient long-context inference — only 12 of 48 layers use KV cache. Built for agentic workflows with strong multilingual support (EN/KO/JA) and 1M context via NoPE.

Models in this family

1 models in the Upstage family, grouped by series. Q4 (GB) is weights-only; total VRAM adds KV cache and overhead — the fit check links compute it for a representative retail GPU at 8K context.

Solar Open 2