.mane🏴‍☠️

Local AI hardware = capacity × bandwidth × software stack - Capacity tells you what fits - Bandwidth tells you how hard the box can breathe - The software stack tells you how much of the spec sheet you can actually cash out. Hardware by Memory Bandwidth - Mac Studio M3 Ultra: up to 512GB @ 819 GB/s - RTX PRO 6000 Blackwell: 96GB @ 1792 GB/s - RTX 5090: 32GB @ 1792 GB/s - RTX 4090: 24GB @ 1008 GB/s - RX 7900 XTX: 24GB @ 960 GB/s - Radeon PRO W7900: 48GB @ 864 GB/s - AMD Radeon AI PRO R9700: 32GB @ 640 GB/s - Intel Arc Pro B65: 32GB @ ~608 GB/s - Tenstorrent Wormhole n300: 24GB @ 576 GB/s - Tenstorrent Blackhole p150: 32GB @ 512 GB/s + 800G - MacBook Pro M5 Max: 460-614 GB/s - MacBook Pro M5 Pro: 307 GB/s - DGX Spark: 128GB @ 273 GB/s (coherent + CUDA) - Mac mini M4 Pro: 273 GB/s - Ryzen AI Max / Strix Halo: ~256 GB/s (~96GB usable GPU) - MacBook Air M5: 153 GB/s - Snapdragon X2 Elite: 152-228 GB/s - Intel Lunar Lake: 136 GB/s - Snapdragon X Elite: 135 GB/s - Mac mini M4: 120 GB/s - Arc Pro B60: 24GB @ ~456 GB/s Verdict - GPUs are still the bandwidth kings - Apple wins: stupid amounts of memory, don’t want to shard across GPUs - Apple loses: when raw tokens/sec & concurrency matter more - DGX Spark: coherent memory + NVIDIA stack - Strix Halo / Ryzen AI Max: first real x86 unified-memory contender - Tenstorrent: fully OSS stack, excited to see this mature Fitting ≠ serving Even if it fits, you still pay for - bandwidth during decode - KV cache growth - dequantization - batching + concurrency - scheduler quality - framework overhead The only mental model that matters: 1. What must fit? 2. What bandwidth tier do I need? 3. What software stack can actually deliver it? In short: - NVIDIA → fastest raw speed - Apple Studio M3 Ultra → biggest one-box memory - Strix Halo → first real x86 unified - DGX Spark → coherent NVIDIA dev appliance - AMD / Intel Arc → rising alternatives - Tenstorrent → fully opensource stack Do ask: “which bottleneck am I buying?” Not: “which hardware is best?”

Today I had an harder than usual question for my local model (security). With SSD streaming now DwarfStar can run DeepSeek v4 PRO at 4.15 t/s, and this was more than enough to get a detailed reply. I already feel "safer" than before in my AI future. M5 max 128GB, model 433GB.

❗❗❗ guys remember this post about codex rate limit resets "on your own time"? well apparently this is some bullshit that is only bankable when you refer people and they sign up for codex tibo's last reset auto-applied i didn't need a reset right now, i had 50% usage in reserve and my reset was tomorrow i could have /fast on xhigh all day and still had a full reset tomorrow but now they forced a reset i didn't need as if it's some reward some anthropic level marketing ngl i was so happy because i thought every reset would be bankable so we could use it when we wanted, on our own time i hate this so much