ai/qwen3-coder-next

Docker

Efficient 80B MoE coding model with 3B activated params, 256K context, and agentic capabilities

ai/qwen3-coder-next-vllm

Docker

Advanced coding agent model with 80B params (3B active MoE) for code generation and debugging

ai/deepcoder-preview

Docker

DeepCoder-14B-Preview is a code reasoning LLM fine-tuned to scale up to long context lengths

ai/phi4

Docker

Microsoft’s compact model, surprisingly capable at reasoning and code

ai/mistral-small4

Docker

119B parameter hybrid model with reasoning, vision, and code capabilities (1M token context)

aistaging/qwen3-coder

aistaging

30.5B MoE coding model with tool calling, browser automation, and 256K context support

Qwen 2.5 coder to use with Docker Model Runner