News for hackers. Stuff that matters.
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by perfobotto on Wednesday July 23, 2025 @09:45AM (#44659185)
No way an offchip HBM has same or better bandwidth then onchip
Re:Cerebras Launches Qwen3-235B, Achieving 1,500 Tokens per ... by 0xCMP on Wednesday July 23, 2025 @11:15AM (#44660158)
> MemoryX has lower latency, but also far lower bandwidth