5060ti-qwen3.8-27b
新上架免费
Deploy a quantized Qwen3.8 27B coding agent locally on a 16GB GPU with llama.cpp, supporting OpenAI-compatible clients and optional Anthropic adapters for real-world repository tasks.
Deploy a quantized Qwen3.8 27B coding agent locally on a 16GB GPU with llama.cpp, supporting OpenAI-compatible clients and optional Anthropic adapters for real-world repository tasks.