Qwen 3.6 and Gemma 4
Alibaba and Google
Qwen 3.6 and Gemma 4 are the compact models. Qwen 3.6 27B and Gemma 4, from 4 to 31 billion parameters, run on a single card, a workstation or at the edge. They suit small businesses.
Key points: Compact · Qwen 3.6 27B and Gemma 4 · Single card · Edge · Small businesses.
Architecture
Qwen 3.6 27B and Gemma 4, from 4 to 31 billion parameters, are the platform's compact models.
Strengths
They run on a single card, a workstation or at the edge, with a reduced memory footprint.
Use cases
These models suit small businesses, embedded uses and tasks where local latency and cost matter more than raw power.
Deployment
Served by llama.cpp or vLLM on DGX Spark, Mac Studio or a single GPU card.
All the models on the platform are interchangeable through a single gateway: switching models is just changing one configuration line, with no code rewrite. Local execution remains the priority.