Fisher Long

一个专注于三维地理空间信息获取与应用的Geek
Focus on geospatial information acquisition and application

[Fisher Long @fisherlong]

@kotohibi_3d nice tools ,have purchased for test

[Ahmad @TheAhmadOsman]

Local AI hardware = capacity X bandwidth X 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?"

[EDU @0xeduu]

🚨EXCLUSIVA: STANFORD ACABA DE FILTRAR GRATIS LA CLASE QUE EXPLICA COMO FUNCIONAN CLAUDE Y CHATGPT POR DENTRO

la mayoria desperdicia el 90% de su potencial

stanford te lo enseña en 1h30 minutos

Guarda esto en favoritos para que no lo pierdas

[Lukas Ziegler @lukas_m_ziegler]

Robots are 3D printing full-size ship hulls! ⚓️

Throwback to when this company 3D printed a boat!

CEAD Group is bringing large-scale robotic 3D printing to the maritime and defense world.

Instead of traditional molds and heavy manual assembly, robotic arms print full-size marine hulls directly from digital models.

The company recently demonstrated this by printing a 12-meter long vessel.

Awesome stuff! 😮‍💨

~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[PlayCanvas @playcanvas]

🚀 PlayCanvas Engine 2.20 is out!

Gaussian Splatting leveled up! Relighting, soft shadows, depth of field, clipping & billions of splats, even in VR under WebGPU.

Plus procedural skies + physics joints & ragdolls.

Free and open source. ✨

npm install playcanvas
[1 / 2]

[Massimo @Rainmaker1973]

Timeline of the Twin Towers

[Over the Reality 🌐 @OVRtheReality]

Large-scale Gaussian splats have reached a new level of realism.

This is a well-known temple in Bangkok, reconstructed as a high-fidelity 3D environment from 360 captures.

At this level, the boundary between video and 3D starts to disappear.

But what you’re looking at is not a video.

It’s a dense spatial representation of a real place, where geometry, texture, and structure are preserved and made machine-readable.

This kind of 3D data can power Visual AI, Robotics navigation, VPS localization, XR experiences, world models, and next-generation spatial computing systems.

Built with Over the Reality.

[Fisher Long @fisherlong]

@theepicmap 加入月球的自转的箭头就更好了

[Fisher Long @fisherlong]

@simplifyinAI nice

[Simplifying AI @simplifyinAI]

One line of code.

That’s all it takes to get access to Google Open Buildings, the largest building dataset, for any country.

100% free and available globally.

[Cesium @CesiumJS]

News: Cesium to continue long-term partnership with @Maxar Intelligence on @USArmy One World Terrain (OWT).

Learn more: https://t.co/ArOIgAwBSc

[Fisher Long @fisherlong]

@MarkWalters_ good jobs

[Fisher Long @fisherlong]

@newgeographer2 nice，How does it work, and what tools are used?

[Fisher Long @fisherlong]

@youwillmakemaps nice

[Fisher Long @fisherlong]

The terrain just like the moon's

[Fisher Long @fisherlong]

@MarkWalters_ mark

[William Long @williamlong]

近日，仲量联行发布了《应势开新，重塑格局：2021中国办公楼市场白皮书》，台北空置率最低，低至2.1%，香港空置率第二低，低至9%；广州、北京、澳门、宁波、杭州、济南的空置率为11%-19.5%。上海、深圳、南京、成都、重庆、苏州、郑州、青岛等城市空置率在20.7%-30%之间。

[Lilium @Lilium]

From Munich to New York, it's been an amazing first day as a publicly listed company on @Nasdaq! Thanks to our incredible team that’s building radically better ways of moving. $LILM #LiliumTakesFlight 🎉

[Fisher Long @fisherlong]

@getlantern 为什么最新版的lartern打开授权设备使用专业版界面是一片空白，已经重新安装最版本包括preview 版本，以管理员界面运行，都不管用

[Fisher Long @fisherlong]

Early Bird Glass - Batu Bolong, 27 June 2021 https://t.co/DZjH3AtJXp 来自 @YouTube