3 models
MiMo-V2.6-Distill-9B (Qwen3.5-9B SFT): coding, agent tasks, visual coding, cybersecurity. Thinking + instruct quants, multimodal.
From https://modelscope.cn/models/OpenBMB/MiniCPM-Llama3-V-2_5
A lightweight, FIM (Fill-In-the-Middle) optimized variant of Qwen2.5-Coder-0.5B-Instruct using the f16 GGUF quantization from HuggingFace. At only ~1 GB, it fits comfortably on any 8 GB single GPU with headroom for 8K context.