Tag
A GGUF quantized version of MiniCPM5-1B-Claude-Opus-Fable5-Thinking model is released on Hugging Face, with usage instructions for llama.cpp, vLLM, and Ollama.
A 1B model with stacked SFT and DPO LoRA adapters achieves human-level scores on the RADAR AI detector, reducing slop phrases to zero, and runs on a 24GB Mac.