Qwen3-Coder-Next 80B A3B

Who should use this model?

• Coding agents, terminal automation, repo edits, and tool calling on 64GB plus workstations or Macs.

Choose something else when

• You have 32GB RAM, expect laptop speed, or need frictionless beginner setup immediately without tuning.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only

Use a smaller model for this memory limit.

8GB system memory

Use a smaller model for this memory limit.

16GB system memory

Use a smaller model for this memory limit.

32GB system memory

Use a smaller model for this memory limit.

8GB GPU memory

Use a smaller model for this memory limit.

12GB GPU memory

Use a smaller model for this memory limit.

24GB GPU memory

Use a smaller model for this memory limit.

Apple unified memory

Use a smaller model for this memory limit.

Model facts that change the decision

Parameters

80B total / 3B active

Input

Text · Code

Published context limit

262,144 tokens

Model format

safetensors · GGUF · Ollama · MLX

Suggested compression

Q4_K_M for first local attempts unless a cited runtime recommends a different default.

Typical Q4 file

48.5GB before runtime and context overhead

Languages

Unknown

Conditions that change the answer

• Although only 3B parameters are active, memory requirements are driven by total model storage, quantization, runtime overhead, and context length.
• Full 256K context may require reducing context length on local systems to avoid out-of-memory errors.
• Best used with current SGLang, vLLM, llama.cpp, Ollama, or LM Studio builds that understand Qwen3-Coder tool formatting.
• Non-thinking model; it is intended for coding-agent behavior, not visible reasoning traces.
• Commercial use: Permitted under Apache-2.0 terms
• Qwen3 Coder Next targets local coding agents: an 80B MoE with only 3B active parameters, strong tool use, and practical workstation deployment when 30B feels underpowered but 480B is impossible for most local builders today.