Skip to content

Qwen2.5-Coder-0.5B-Instruct-AWQ

A 0.5B AWQ-quantised code generation model

Visit official site

What Qwen2.5-Coder-0.5B-Instruct-AWQ is

The model is described as an AWQ 4-bit quantised 0.5B variant of the Qwen2.5-Coder series built on a transformers architecture.

What you can do with it

  • Generate code from a prompt
  • Reason about code logic
  • Detect and repair code errors

Application scenarios

  • A developer generates sorting algorithm code
  • An engineer fixes errors in existing code
  • A teacher explains code logic to students

Pros & cons

✓ What we like

  • Code generation, reasoning and repair are covered
  • Maths and general abilities are retained

! What to watch out for

  • It is the 0.5B parameter variant
  • Loading uses AutoModelForCausalLM and AutoTokenizer

FAQ

What quantisation is used?

The material states AWQ 4-bit quantisation.

How large is the training set?

The series extended training tokens to 5.5 trillion.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review