Qwen2.5-Coder models

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. - Provider: Alibaba Cloud (Qwen Team) - Released: 2024-11-12 (GA) - Tier: Coder (coding specialist) - Context: 131,072 tokens - Max output: 8,192 tokens - Modalities: text (code-specialized) - Knowledge cutoff: approx. 2024-08 - Headline price: approx. $0.08 in / $0.24 out per 1M tokens (blended)