sunkencity/qwen25-3b-openclaw
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Mar 19, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

sunkencity/qwen25-3b-openclaw is a 3.1 billion parameter Qwen2.5-3B-Instruct model fine-tuned by sunkencity for exceptional tool/function calling abilities. Optimized for use as a local agent model within the OpenClaw/LocalClaw framework, it excels at structured function calls and argument extraction. This model is designed for offline, privacy-first deployments, running efficiently on Apple Silicon or modest GPUs with a 32768 token context length.

Loading preview...