qwen3-0.6b/README.md

Qwen3-0.6B

Run Qwen3-0.6B locally with ollama or llama.cpp.

Setup

nix develop

Usage

ollama

ollama serve &
ollama run qwen3:0.6b

llama.cpp

# Download a GGUF from https://huggingface.co/Qwen/Qwen3-0.6B-GGUF
llama-cli -m Qwen3-0.6B-Q4_K_M.gguf -p "Hello" -cnv