A developer just squeezed this 284B-parameter DeepSeek model into 64GB of regular DDR5…
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
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 develo
Posted by David Hendrickson (12.8k followers) 22 min ago · 0 likes · 74 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- In the Code Arena: WebDev, Inkling 2 Small by @thinkymachines is #5 in Data & Analytics! — @arena
- Clover-35B-A3B decodes at 61.8 tok/s on a 16 GB RTX 5060 Ti, 2.4x faster than BF16 on… — @niklaslenz_ai
- Your AI trip plan shouldn’t need copying into another app. — @DanKornas
- A lot of people say OpenAI's computer use is better than Claude's, I don't think so… — @dwhitedesign
- This tiny chip lets an AI use your iPhone for you. — @VaibhavSisinty
- Why do we need WebMCP when a backend API already does the job? — @ChromiumDev
- 又变聪明了！Claude Code 云端 session 终于学会自己配环境了！ — @NFT_Chen
- Does anyone know if the Artificial Analysis decisions index is good? — @AdamHoltererer
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.8k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 21:47 UTC. Full method.