Agent-Ark/Toucan-Qwen2.5-7B-Instruct-v0.1
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Oct 2, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Agent-Ark/Toucan-Qwen2.5-7B-Instruct-v0.1 is a 7.6 billion parameter instruction-tuned model based on Qwen2.5-7B-Instruct, developed by Agent-Ark. It is specifically fine-tuned on the Toucan-1.5M dataset, which comprises over 1.5 million synthetic tool-agent trajectories. This model excels at complex tool-use scenarios, outperforming larger models on benchmarks like BFCL V3 and MCP-Universe, making it ideal for developing advanced agentic LLMs.

Loading preview...