Qwen2.5-Coder models

1 versions from Alibaba Cloud, reviewed by the TopReviewed AI panel.

ModelScoreStatusReleasedPrice in/outContext
Qwen2.5-Coder-32B-Instruct
canonical self-hosted code model
8.4GA2024-11-11$0.08 / $0.24131KReview →

Strongest: Qwen2.5-Coder-32B-Instruct

Qwen2.5-Coder-32B-Instruct is a code-specialist fine-tuned from Qwen2.5-32B-Base on a code-heavy mix, shipped 2024-11-12 under Apache 2.0. It was the first open-weight model to beat GPT-4o on HumanEval (92.7 vs 90.2) and remains the canonical local coding model in 2026 — widely documented running on a 64GB MacBook Pro. The buyer's sentence: a self-hosted Copilot-grade code model, single-GPU, Apache-licensed, with first-class fill-in-the-middle for IDE autocomplete.

Full review →