Issue 2026-11-20 · Industry · 模型发布 · 开源
Hugging Face ships Inkling 2 Mini for local setups

Inkling 2 Mini is a multimodal Mixture-of-Experts model for local deployment with ~26B total and 3B active parameters, looping layers and a 1M-token context. It is said to be at least comparable to Qwen 3.8 27B, with transformers, llama.cpp and MLX support.
Read original ↗