Alibaba Cloud • 32.5 Billion128,000 Token Context

Qwen 2.5 Coder 32B Token Pricing & VRAM Calculator

Best-in-class local coding model capable of running entirely on a single 24GB consumer GPU. Ideal for: Local offline coding, full-repository comprehension, code generation.

API Cost (per 1M Tokens)

$0.30 / 1M Input

$0.60 / 1M Output

100k input tokens = ~$0.0300 | 100k output = ~$0.0600

Local VRAM & GPU Specs

24 GB

Single RTX 3090 / RTX 4090 (24GB VRAM)

Local Ollama Run

ollama run qwen2.5-coder:32b

Inspect port 11434: Port 11434 Guide

Compare Other AI Foundation Models

GPT-4o (Omni)$2.5/1M in Claude 3.5 Sonnet$3/1M in DeepSeek R1 (Reasoning)$0.55/1M in Llama 3.3 70B Instruct$0.7/1M in Mistral Small 3 (24B)$0.2/1M in

Frequently Asked Questions

How much does Qwen 2.5 Coder 32B cost per 1M tokens?

Qwen 2.5 Coder 32B costs $0.30 per million input tokens and $0.60 per million output tokens.

What GPU is needed to run Qwen 2.5 Coder 32B locally?

Qwen 2.5 Coder 32B requires at least 24GB VRAM for 4-bit quantization. Recommended hardware: Single RTX 3090 / RTX 4090 (24GB VRAM).

What is the context window size of Qwen 2.5 Coder 32B?

Qwen 2.5 Coder 32B supports a context window of 128,000 tokens.