Qwen 2.5 Coder 32B
Instruction-tuned coding specialist for generating, explaining and fixing code. Compare outputs on your own programming tasks.
The Ollama artifact and published model specifications were checked. Memory figures are conservative MamiLens planning estimates, not a speed result from your device.
- Official model source
- Official engine artifact
Will it run?
MamiLens uses 30 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 qwen2.5-coder:32bStart 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: 32K published max. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.