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: Apple M6 Rumored to Pack Dual Neural Engines with 4.8x AI Gains(3 posts)→
More from Embodied
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16
- NVIDIA RTX Spark PC launches tomorrow with global events and strong early reviews — NVIDIA Blog · 2026-10-16