Apple M6 leaks claim 4.8x faster LLM inference, local 70B model support
kimmonismus · x · 2026-08-25
Leaks suggest Apple is preparing M6 and M5 Ultra chips for a "big leap in AI compute."
M6 Key Specs:
- Performance: Up to 4.8x faster LLM prompt processing than the M4.
- Memory: 42% higher bandwidth at 170GB/s, up to 32GB unified memory.
- Architecture: 12-core CPU/GPU, dual 16-core Neural Engine.
M5 Pro: Specifications scale even higher.
Impact: Capable of running quantized 70B-class models locally.
Related event: Rumor: Apple M6 Gets Dual Neural Engines for Big AI Boost(2 posts)→
More from Embodied
- Bottleneck for robotics in UK manufacturing is adoption, not capability, says CTO — stepjamUK · 2026-08-25
- Unitree Robot Gets Lost During 400m Obstacle Race at Humanoid Games — saibharadwaj · 2026-08-25
- Gatik raises $200M Series D at $1B valuation for driverless middle-mile freight — kimmonismus · 2026-08-25
- Apple's M6 Chip Reportedly Adds Dual Neural Engines — BenBajarin · 2026-08-25
- Intel Arc Pro B60 Dual 48GB spotted in retail channels — reto-wyss · 2026-08-25
- Waymo announces expansion to Germany, its second European city — reed · 2026-08-25