Qwen 3 Coder Next 80B-A3B
A coding specialist for repository work, code changes and agent tools. Its 3B active parameters do not reduce the full 80B model download.
Exact local Ollama manifest and configuration checked on 2026-10-20. Memory figures are conservative planning estimates; no DeviceTerra inference or speed test is claimed. Requires Ollama 0.15.5 or newer. Store the complete 80B weights; 3B active does not mean a 3B download.
- Official model source
- Official engine artifact
Will it run?
MamiLens uses 79 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.
Check your complete system →What is it useful for?
Suggested Ollama artifact
Confirm the tag on the official page before downloading, then run:
ollama run qwen3-coder-next:q4_K_MStart with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.
Evidence and limits
Published context: 256K artifact maximum; practical context depends on memory. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.