mgonzs13/llama_ros

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek

Distribute and run LLMs with a single file.

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-cor

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.