276B total parameters, 12B active, 1M context window. Blog post: https://thinkingmachines.ai/news/inkling-small/ NVFP4: https://huggingface.co/thinkingmachines/Inkling-Small-NVFP4 GGUF's by Unsloth: https://huggingface.co/unsloth/Inkling-Small-GGUF