Unsloth Inkling 2 Small GGUF: Quantization options, local execution with llama.cpp
AI-generated summary Unsloth distributed smaller GGUF weight files and quantizations for the Inkling 2 Small model to allow local execution using llama.cpp. Thinking Machines Lab released the model weights on Hugging Face on November 12, following its announcement on November 5, 2026.