Announcing Redis 8.6: Performance Improvements, Streams Enhancements, New Eviction Policies and More

Blog written by Lior Kogan, Principal Product Manager, Redis published Feb. 10, 2026

Redis 8.6 in Redis Open Source is now available. This release delivers performance and resource utilization improvements, plus a set of community-requested updates that make day-to-day development and operations smoother. It includes new Streams safeguards, more eviction control, better hotkey visibility, simpler TLS auth, and more flexible time series handling.

• Performance and resource utilization improvements in Redis 8.6
• New features explained:
  • Streams: At-most-once production guarantee
  • Eviction: Least recently modified policies
  • Hotkeys: Detection and reporting
  • Security: TLS certificate-based automatic client authentication
  • Time series: Support for NaN values

With Redis 8.6 in Redis Open Source, we continue to deliver on our commitment to continuous performance improvement. The chart below shows our steady throughput increase (operations per second) for a typical caching workload use case across successive releases of Redis. 

Redis 8.6 in Redis Open Source: More than 5x throughput compared to Redis 7.2
Redis performance improvements are not limited to better multithreading. We continuously reduce the latency of many commands. Compared to Redis 8.4, in Redis 8.6, we achieved:

• Up to 35% lower latency for sorted set commands
• Up to 15% lower latency for GET command on short strings
• Up to 11% lower latency on list commands
• Up to 7% lower latency on hash commands

Redis 8.6 max latency improvement compared to Redis 8.4 (single core)
The throughput and latency improvements are similar on Intel and AMD processors.

In addition, in 8.6 we achieved a tremendous reduction in the memory footprint of hashes and sorted sets – up to 16.7% and 30.5% respectively.

Redis 8.6 max memory reduction by data type compared to Redis 8.4
Compared to Redis 8.4, in Redis 8.6, we improve vector sets vector insertion performance by up to 43% and querying performance by up to 58%.