docs: add LLM quantization tiers table (q4km/q5km/q8)

docs: add install/run instructions (Releases + download script + landing) and q8

add Q5_K_M LLM (551MB, CER 8.25)

Upload qwen3-0.6b-q4km.gguf with huggingface_hub

Upload qwen3-0.6b-q8_0.gguf with huggingface_hub

Upload funasr-encoder-f16.gguf with huggingface_hub

Upload README.md with huggingface_hub

initial commit