RAM and CPU is DEAD ☠️

You asked for it, so here it is. Visualizing... CPU cache speeds relative to RAM. Cache optimization is important too!show more

POV: your agent has a desktop in the cloud... 8 CPU, 16Gi RAM, $0.00025/second the future is hereshow more

One hole and you will dead ☠️

AYATOLLAH KHAMENEI IS DEAD ☠️💃🏻 #ThankYouPresidentTrump

The Windows 11 Start Menu is comically bad. This... machine has a $1600 Core i9 CPU and 128 GB of RAM and this is the performance I often get. What is going on in Redmond?show more

Ram Ram Bhai Sara Ne 🙏💪🚩☠️

Real life Mario Kart in Vietnam is a dead trap☠️

I'm dead.. ☠️🤣🤪

I’m dead already ☠️ 🤦‍♂️

Can I still say that this is gonna raise... RAM prices or is that joke just dead now?show more

How do Perceptron nodes work? They use idle bandwidth.... Not your CPU. Not your RAM. Simple. Light. Rewarding.show more

#Ramayana is the story of Shree Ram. Shree Ram... is played by Ranbir Kapoor. Ranbir Kapoor is Ram. And without Ram, Ramayana is like Yash without Neelshow more

Hey you guys wanna see a dead body? ☠️

Dead Boy Detectives moments that make you go ☠️

I'm dead. ☠️🤣 This is my absolute favorite clip... of Putin... Dudes are gonna be dudes. 🤣🤣show more

A developer just squeezed this 284B-parameter DeepSeek model into... 64GB of regular DDR5 RAM. 🤯 And it's running with 0 GPUs! Very cool that with just a CPU, 64GB RAM, and some intelligent engineering, you can run DeepSeek. This is llama-modchip. GitHub dev synchopate has published a modified llama.cpp inference stack capable of running DeepSeek-V4-Flash entirely in system memory. Here's the setup 🧠 DeepSeek-V4-Flash 🔥 284.33B total / ~13B active 💾 64GB DDR5 RAM 🎮 ZERO GPUs 📚 256K configured context ⚙️ Custom AVX2 / AVX-512 CPU kernels 🔓 Source code available on GitHub Here are some developer-reported numbers Memory 🐌 Previous quant → 76.87 GiB 🚀 Optimized quant → 56.56 GiB 💾 Actual process RAM → 57.61 GiB 26.4% reduction in model storage, enough to bring it below the 64GB RAM limit. And the inference performance? ⚡ CPU decode → 9.1–14.7 tps (very usable) 📥 Prompt processing → 44.36 tps Prefill before optimization: 🐌 25.05 tps Prefill after optimization: 🚀 44.36 tps That's 77.1% FASTER prompt processing, damn So how did they do it? The developer combined these 🧠 Low-bit quantization 🔧 Specialized AVX2 / AVX-512 CPU kernels ⚡ Better reuse of weights across prompt tokens 💾 CPU cache tiling across registers, L1, L2 and L3 🔬 MoE expert and attention optimizations Making hardware do things it was never supposed to do. 🔥show more