DEV Community

#nvidia

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Simple Benchmark Review: Ollama on Jetson Nano

High accuracy at low quantization
annavi11arrea1 profile

Simple Benchmark Review: Ollama on Jetson Nano

#ai #webdev #nvidia #productivity
41
Comments 39
4 min read
July closed with $55.8 billion in Physical AI funding and an industry finally stopped asking whether this works. Here's what you missed this week.
xberry-tech profile

July closed with $55.8 billion in Physical AI funding and an industry finally stopped asking whether this works. Here's what you missed this week.

#humanoidrobots #physicalai #neurarobotics #nvidia
Comments
9 min read
Building Hardware-Accelerated FFmpeg on NVIDIA Jetson AGX Orin 64GB
vonusma profile

Building Hardware-Accelerated FFmpeg on NVIDIA Jetson AGX Orin 64GB

#nvidia #ai #ffmpeg #tutorial
1
Comments
3 min read
Nvidia's water-saving cooling fixes the wrong half of AI
induwara_ashinsana_9e4d5b profile

Nvidia's water-saving cooling fixes the wrong half of AI

#aisustainability #datacenters #nvidia
Comments
4 min read
I Moved My AI Stack From NVIDIA to Apple Silicon. Then I Moved Back. Here's Why.
samhartley_dev profile

I Moved My AI Stack From NVIDIA to Apple Silicon. Then I Moved Back. Here's Why.

#ai #applesilicon #nvidia #selfhosted
Comments
5 min read
GB10 實測 DiffusionGemma 26B 挑戰 32K 極限
jh5_pulse profile
JH5

GB10 實測 DiffusionGemma 26B 挑戰 32K 極限

#nvidia #blackwell #gb10 #diffusiongemma
Comments
3 min read
DiffusionGemma 26B 挑戰 GH200 效能極限
jh5_pulse profile
JH5

DiffusionGemma 26B 挑戰 GH200 效能極限

#ai #nvidia #benchmark #llm
1
Comments
2 min read
How to Review an Edge LLM Benchmark Without Fooling Yourself
roronoa_ profile

How to Review an Edge LLM Benchmark Without Fooling Yourself

#edgeai #nvidia #ai #performance
Comments
2 min read
Qwen3.6-35B NVFP4 runs on one H100 — A100 owners are out
creeta profile

Qwen3.6-35B NVFP4 runs on one H100 — A100 owners are out

#qwen3 #nvfp4 #vllm #nvidia
Comments
8 min read
Nemotron 3 Ultra went live June 4. Here's the call that works.
creeta profile

Nemotron 3 Ultra went live June 4. Here's the call that works.

#nvidia #nemotron #openweights #llm
Comments
7 min read
Stable Diffusion Inference: Memory Requirements, Speed and GPU Selection
daya-shankar profile

Stable Diffusion Inference: Memory Requirements, Speed and GPU Selection

#nvidia #gpu
Comments
7 min read
Why cudaMalloc fails on NVIDIA Jetson Orin Nano Super — and the one flag that fixes it
hemkesh2021dotcom profile

Why cudaMalloc fails on NVIDIA Jetson Orin Nano Super — and the one flag that fixes it

#jetson #nvidia #cpp #edgeai
Comments
2 min read
The end of hardcoded model prompts: Building agents that discover their their own infrastructure
renato_marinho profile

The end of hardcoded model prompts: Building agents that discover their their own infrastructure

#mcp #ai #llm #nvidia
Comments 1
4 min read
oMLX 效能調校 KV Cache 與Concurrent Batching
jh5_pulse profile
JH5

oMLX 效能調校 KV Cache 與Concurrent Batching

#ai #nvidia #llm
Comments
9 min read
NeMo Agent Toolkit ：K8s 沙箱逃逸、付款劫持
jh5_pulse profile
JH5

NeMo Agent Toolkit ：K8s 沙箱逃逸、付款劫持

#security #kubernetes #nvidia #nemo
Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.