Qwen3.5-27B (Qwen Chat) is a post-trained, chat-optimized large language model released in Hugging Face Transformers format. It’s designed for strong general-purpose performance across reasoning, coding, and agentic tasks, and is compatible with popular inference stacks like Transformers, vLLM, and SGLang. Qwen3.5 emphasizes improved efficiency and scalability, with broader multilingual coverage and training advances aimed at high-utility real-world deployment.
Fine-tuningDocs | Qwen3.5 27B can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments allow you to use Qwen3.5 27B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
