DEV Community

#hardware

Discussing monitors, tablets, laptops, and other design hardware

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why GPU Memory Bandwidth Matters More Than VRAM for Local LLMs
billybobgurr profile

Why GPU Memory Bandwidth Matters More Than VRAM for Local LLMs

#ai #llm #opensource #hardware
Comments
2 min read
RTX 5090, LLaMA.cpp TurboQuant, & Blackwell CUDA Scheduling Boosts GPU Performance
soytuber profile
soy

RTX 5090, LLaMA.cpp TurboQuant, & Blackwell CUDA Scheduling Boosts GPU Performance

#gpu #nvidia #hardware
1
Comments
3 min read
How Much RAM Do You Really Need to Run LLMs Locally? 2026 Benchmarks
pavelespitia profile

How Much RAM Do You Really Need to Run LLMs Locally? 2026 Benchmarks

#ai #ollama #hardware #beginners
1
Comments
6 min read
Why Most Browser AI Demos Fail on Real Hardware
bruno_juca_7038c22bcca1db profile

Why Most Browser AI Demos Fail on Real Hardware

#ai #inference #hardware #benchmark
Comments
4 min read
Stop picking a homelab mini-PC by TDP. The number that decides the power bill is idle watts.
jvancedev profile

Stop picking a homelab mini-PC by TDP. The number that decides the power bill is idle watts.

#homelab #selfhosted #hardware #proxmox
1
Comments 1
4 min read
CUDA-Oxide 0.1, RTX 5070 Launch, & BeeLlama.cpp Boost 3090 Inference
soytuber profile
soy

CUDA-Oxide 0.1, RTX 5070 Launch, & BeeLlama.cpp Boost 3090 Inference

#gpu #nvidia #hardware
Comments
3 min read
Building 24/7 Digital Signage Systems: 8 Practical Ways to Reduce LCD Image Retention
alan12 profile
Alan

Building 24/7 Digital Signage Systems: 8 Practical Ways to Reduce LCD Image Retention

#hardware
Comments
3 min read
What is a Mobile AI Agent? The Architecture, Limits, and Hardware Problem (2026)
nataiden profile
Nat

What is a Mobile AI Agent? The Architecture, Limits, and Hardware Problem (2026)

#ai #mobile #hardware #llm
Comments
4 min read
CUDA-Oxide 0.1 Lands; RTX 5090 Launches with 32GB & Hits 600 Tok/s
soytuber profile
soy

CUDA-Oxide 0.1 Lands; RTX 5090 Launches with 32GB & Hits 600 Tok/s

#gpu #nvidia #hardware
Comments
3 min read
AMD MI350P, CUDA WarpReduction, & Adrenalin 26.5.1 Driver Updates
soytuber profile
soy

AMD MI350P, CUDA WarpReduction, & Adrenalin 26.5.1 Driver Updates

#gpu #nvidia #hardware
Comments
3 min read
Beyond Temperature Polling - Designing an Event-Driven Cold Chain Telemetry Stack
applekoiot profile

Beyond Temperature Polling - Designing an Event-Driven Cold Chain Telemetry Stack

#iot #embedded #hardware #architecture
Comments
5 min read
RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers Emerge
soytuber profile
soy

RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers Emerge

#gpu #nvidia #hardware
Comments
3 min read
The ASIC Unbundling
david_aronchick_ea415de50 profile

The ASIC Unbundling

#aiinfrastructure #distributedsystems #hardware #silicon
Comments
7 min read
AMD Ryzen AI Max+ PRO 495 Leak, RTX 5080 Tease, & Interactive CUDA Lessons
soytuber profile
soy

AMD Ryzen AI Max+ PRO 495 Leak, RTX 5080 Tease, & Interactive CUDA Lessons

#gpu #nvidia #hardware
Comments
3 min read
The Ultimate AI Shortcut That Wasn't
al-chris profile
Chris

The Ultimate AI Shortcut That Wasn't

#kicad #ai #hardware #automation
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.