antiableofnormies/qwen3-8b-lora-android-dev-gguf

Qwen3-8B LoRA GGUF — Android Code Style

Converted from antiableofnormies/qwen3-8b-lora-android-dev.

Usage with llama.cpp

# Download base model
# e.g. Kondara/Qwen3-8B-Q4_K_M-GGUF or tensorblock/Qwen_Qwen3-8B-GGUF

# Run llama-server with LoRA
llama-server   -m Qwen3-8B-Q4_K_M.gguf   --lora qwen3-8b-lora-android-dev.gguf   --port 8080   -ngl 99

Training Details

See parent LoRA repo for training details.