Skip to main content
Qwen /

Qwen2.5-Coder-32B-Instruct

accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope

LLMTunableChat

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Note: This model is served experimentally as a serverless model. If you're deploying in production, be aware that Fireworks may undeploy the model with short notice.

Fine-tuning

Qwen2.5-Coder-32B-Instruct can be fine-tuned on your data to create a model with better response quality. Fireworks uses low-rank adaptation (LoRA) to train a model that can be served efficiently at inference time.

See the Fine-tuning guide for details.

Fine-tune this model

On-demand deployments

On-demand deployments allow you to use Qwen2.5-Coder-32B-Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

See the On-demand deployments guide for details.

Deploy this Base model