We promised open weights for Qwen3.8. Now, time to meet them! 🎉
⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M
Check out my latest article: One Job, 10,000 Tables: Production Practices for Large-Scale Lake Ingestion with Flink CDC and Apache Paimon linkedin.com/pulse/one-job-…@LinkedIn
Visitar URL original
