Ready-made INT4 W4A16 build (compressed-tensors): 9B dense LLM from the Qwen3.5 generation (02.2026). Strong reasoning, coding and multilingual chat.
Dense 9B model of the Qwen3.5 generation (released 02.2026). Outperforms the Qwen2.5 line in reasoning, coding and agents.
Primary general-purpose assistant model. Runs on a single 24GB GPU at bf16 (weights ~19.3 GB).
