Tag feed

#apple-silicon

39 posts6 followers

Explore Hashnode

Alternatives

Trending tags this week

KKhaskykhasky.hashnode.dev11h ago · 5 min read

Edge0 streams MoE experts off SSD to fit 35B in 3 GB

One question took me through Edge0: if the 35B model only needs 2.9 GB of RAM, what does the machine actually need? The answer is a disk budget, a cache budget and a context budget, and none of them i

0

BMBillie Mbilliem.hashnode.dev2d ago · 7 min read

Local models are actually good now - playing with Qwen3.8-27B

All three quantisations of Qwen3.8-27B loaded on my 48 GB M4 Pro. Only two survived a complete 25-iteration Pi session. The 8-bit model was not rejected at startup. It ran for 32 minutes, produced a s

0

OJOliver Januaryneutrontech.hashnode.devAug 31 · 12 min read

Is Cloud Indexing Necessary? A Guide to Local-First Workspace Software

Modern workspace software has made search, collaboration, and AI remarkably convenient. But does a workspace really need to send its information to the cloud to be intelligent, searchable, and useful?

0

MSManu Shuklaecorpit.hashnode.devAug 3 · 15 min read

Apple Silicon vs cloud APIs in 2026: the local LLM break-even, with real benchmarks

Apple Silicon vs cloud APIs in 2026: the local LLM break-even, with real benchmarks Summary. As of 4 August 2026 Apple's Mac Studio specification page lists exactly 2 chips: M4 Max at 410GB/s of memor

0

MSManu Shuklaecorpit.hashnode.devJul 18 · 13 min read

PyTorch 2.13 on Apple Silicon: FlexAttention is up to 12x faster than SDPA

PyTorch 2.13 on Apple Silicon: FlexAttention is up to 12x faster than SDPA Summary. PyTorch 2.13, released around July 11, 2026, brings FlexAttention to Apple Silicon through the Metal (MPS) backend,

0

MSManu Shuklaecorpit.hashnode.devJul 18 · 12 min read

PyTorch 2.13 brings FlexAttention to Apple Silicon: a 12x sparse-attention speedup

PyTorch 2.13 brings FlexAttention to Apple Silicon: a 12x sparse-attention speedup Summary. PyTorch 2.13 shipped on July 8, 2026, and for anyone training or running models on a Mac the headline is one

0

TLTina Ldebugnote.hashnode.devJul 5 · 2 min read

Microsoft Store Stuck on Loading in Windows 11 on Parallels (M1 Mac)

Microsoft Store appears to work normally, but every app download stays on “Loading” after clicking Get or Install. No error is shown. The download simply never starts. Environment Mac: Apple Silicon

0

たたかおかniixo.hashnode.devJun 22 · 3 min read

Why Chromium/CEF apps render a black window under Wine (and how to fix it with macOS IOSurface)

The problem I was trying to run a Windows-only Steam game on an Apple Silicon Mac using a self-built Wine + DXMT (D3D11→Metal) stack — no commercial CrossOver. The last wall: the window opens, but its

0

Ssatyasutarprimitives.hashnode.devJun 13 · 11 min read

Building an Enterprise Second Brain Locally with MLX + OpenCode

What Is an Enterprise Second Brain? The term "second brain" was popularized by productivity thinkers as a way to describe an external system for capturing, organizing, and retrieving knowledge — freei

0

SSurajblog.surajdev.techApr 30 · 18 min read

How I Run a Full AI Coding Stack Locally Zero Cost, Zero Cloud, Zero Compromise

Before We Start, What You'll Actually Get From This This is not a "look what AI can do" post. This is a documented, real-world setup guide written by a DevOps engineer who got tired of sending infrast

0

#apple-silicon

Search Hashnode

#apple-silicon

Explore Hashnode

Trending tags this week

Edge0 streams MoE experts off SSD to fit 35B in 3 GB

Local models are actually good now - playing with Qwen3.8-27B

Is Cloud Indexing Necessary? A Guide to Local-First Workspace Software

Apple Silicon vs cloud APIs in 2026: the local LLM break-even, with real benchmarks

PyTorch 2.13 on Apple Silicon: FlexAttention is up to 12x faster than SDPA

PyTorch 2.13 brings FlexAttention to Apple Silicon: a 12x sparse-attention speedup

Microsoft Store Stuck on Loading in Windows 11 on Parallels (M1 Mac)

Why Chromium/CEF apps render a black window under Wine (and how to fix it with macOS IOSurface)

Building an Enterprise Second Brain Locally with MLX + OpenCode

How I Run a Full AI Coding Stack Locally Zero Cost, Zero Cloud, Zero Compromise