Today for AI
HOT RADAR
computeHEAT 10.4°

AI CURATED HOT STORY · 10/31/2026

XHEART Launches X7 Ultra Chip with High NPU Utilization and Quantization Precision

1 reports archived1 independent sourcesupdated 10/31/2026, 13:11:19
Synthesis & Latest Updates
1 Sources Cross-Validated

Momenta-affiliated chipmaker XHEART unveiled its first automotive AI chip, the X7 Ultra, delivering 700 TOPS of compute. The chip emphasizes 'Large Model Compute' metrics, achieving 98.7% NPU utilization and over 99.99% similarity between quantized outputs and FP32 baselines, aiming to address idle compute and precision loss in autonomous driving scenarios.

LATEST/Momenta-affiliated chipmaker XHEART unveiled its first automotive AI chip, the X7 Ultra, delivering 700 TOPS of compute. The chip emphasizes 'Large Model Compute' metrics, achieving 98.7% NPU utilization and over 99.99% similarity between quantized outputs and FP32 baselines, aiming to address idle compute and precision loss in autonomous driving scenarios.

Hourly heat curve

7 fully observed hours
Now
10.4
Peak
11.814:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. 量子位官网T2·68 pts

    XHEART Launches X7 Ultra Chip with High NPU Utilization and Quantization Precision

    • The X7 Ultra chip achieves 98.7% NPU utilization, significantly reducing memory bandwidth consumption and improving energy efficiency.
    • Introduces 'Large Model Compute' evaluation standards based on real production autonomous driving models rather than theoretical TOPS alone.
    • Quantization breakthrough: Maintains over 99.99% similarity between quantized outputs and FP32 baseline models while compressing compute requirements.