Axera unveils AX8860 6nm edge AI chip series with up to 256 TOPS
Overview
Axera unveiled the AX8860, a 6-nanometer edge AI chip series for factory, warehouse and robotics use, at CIIF 2026 in Shanghai.
The company says the chips deliver up to 256 TOPS of mixed-precision compute with native FP4 support, up to 273 GB/s of memory bandwidth, and as much as 128 GB of LPDDR5X memory.
Axera says the chips support vLLM, SGLang, PyTorch and an OpenAI API-compatible service interface. Sipeed claims that on a Qwen 27B run the AX8860 delivers about 25% faster prefill and 30% faster decode than an NVIDIA DGX Spark. That comparison is Sipeed's own claim, not a third-party benchmark, and it does not appear in Axera's announcement.
Written by AI from the articles below · updated Oct 16, 3:51 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- PandailyNewsAxera unveils AX8860 edge AI chip series with 256 TOPS and up to 128 GB memory
AIAxera unveiled the AX8860, a 6-nanometer edge AI chip series for factory, warehouse, and robotics use, with up to 256 TOPS and 128 GB of LPDDR5X memory. The company says it supports vLLM, SGLang, PyTorch, and an OpenAI API-compatible service interface. Sipeed claims about 25% faster prefill and 30% faster decode than an NVIDIA DGX Spark on a Qwen 27B run, but that is not a third-party benchmark and is absent from Axera's announcement.
Heat trend
- Current comparable heat
- 9
- Peak comparable heat
- 10Oct 16, 4:00 AM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.