Overview
Qwen3-Coder-30B-A3B-Instruct is a coding-focused large language model built by Qwen (Alibaba's model team). It uses a Mixture-of-Experts (MoE) architecture with 30.5B total parameters, but only about 3.3B are active on any given token because the router picks 8 of its 128 experts per forward pass. That design gives it the knowledge of a 30B model while running at the speed and memory cost closer to a much smaller dense one.
In Atomic Chat the model runs fully on your own machine. Weights load locally, inference happens on your CPU or GPU, and nothing about your prompts or code leaves the device. You can keep working with it offline once the download finishes, which suits private repositories and sensitive work where sending code to a cloud API is not an option.
What it is good at
This is an agentic coding model, instruction-tuned for writing, editing, and reasoning over code across many languages. Its real strengths line up with the capabilities it ships with.
- Agentic coding — it handles multi-step coding tasks and tool calls, with a function-call format designed to drive agent loops in setups like Qwen Code and CLINE.
- Long-context work — a 256K native window lets it read across a whole repository, follow imports, and answer questions that span many files instead of one snippet at a time.
- Multilingual code reasoning — it works across mainstream programming languages and natural languages, so it can explain a bug, refactor a function, or write tests in the language you ask in.
Running it locally
The model is 30.5B parameters with a 256K context length. Because the MoE design keeps active parameters near 3.3B, a 4-bit quant (Q4_K_M) fits in roughly 18-22GB of VRAM, and people report 12-15 tokens per second on a modern CPU with 32GB of RAM at that quant. Full FP16 weights need around 67GB, so most local users run a quantized build.
huggingface-cli download Qwen/Qwen3-Coder-30B-A3B-Instruct
From there you can load it with Hugging Face Transformers or serve it through vLLM, or skip the setup and open it in Atomic Chat, which downloads and loads the model with one click.
License
Qwen3-Coder-30B-A3B-Instruct is released under the Apache 2.0 license. That permits commercial use, modification, and redistribution, including in closed-source products, as long as you keep the license and attribution notices.