Best coding models

From 1 B autocomplete to 14 B agentic refactoring

Code-specialised models ranked by HumanEval-class performance. Pair with Cursor / Continue / Aider for an offline copilot.

  1. 1

    Alibaba

    Qwen 2.5 Coder 14B

    Powerful 14B code model. Excellent for complex programming tasks.

    14B≥ 8.87 GB
  2. 2

    Alibaba

    Qwen 2.5 Coder 7B

    Strong 7B code model rivaling larger coding models. Excellent for local development.

    7.6B≥ 4.86 GB
  3. 3

    Alibaba

    Qwen 2.5 Coder 3B

    Capable 3B code model. Good balance of coding ability and resource usage.

    3B≥ 2.46 GB
  4. 4

    Alibaba

    Qwen 2.5 Coder 1.5B

    Compact code model with solid code generation and understanding abilities.

    1.5B≥ 1.54 GB
  5. 5

    DeepSeek

    DeepSeek Coder 6.7B

    Powerful 6.7B code model with excellent code generation across many languages.

    6.7B≥ 4.3 GB
  6. 6

    Google

    CodeGemma 7B

    Google's instruction-tuned code model. Strong code generation and understanding.

    8.5B≥ 5.46 GB
  7. 7

    BigCode

    StarCoder2 7B

    Larger code model with better completions.

    7B≥ 4.66 GB
  8. 8

    01.AI

    Yi Coder 9B

    Strong 9B code model with good reasoning.

    9B≥ 5.46 GB

Not sure which fits your machine? Auto-detect your hardware →