llama.cpp adds native tools, Qwen releases 35B GGUF model

The llama.cpp project has integrated native tools, including shell command execution and file editing, directly into its server, enabling local large language models to perform actions and automate tasks. This advancement facilitates the creation of more capable autonomous agents that can operate entirely on local hardware. Additionally, a new 35-billion parameter Qwen model, Qwen3.6-35B-A3B, has been released in the GGUF format, optimized for efficient local inference on consumer hardware. AI

IMPACT Enhances local AI agent capabilities and accessibility of large open-weight models on consumer hardware.

RANK_REASON The cluster details updates to open-source tools and model releases for local inference, rather than a frontier model release from a major lab. [lever_c_demoted from research: ic=1 ai=0.7]

Read on dev.to — LLM tag →

• edit_file
• exec_shell
• GGUF
• llama.cpp
• Ollama
• Qwen3.6-35B-A3B

• model release
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →