DeepSeek V4 Flash Fully Local — 32 tok/s on a Single Chip

Save to stack
Fahd Mirza Open on YouTube ↗
DeepSeek V4 Model Developers Audience Technical Level Course Format
From the creator

Running a 284 billion parameter DeepSeek V4 Flash model completely locally on a single AMD Ryzen AI MAX+ 395 with 128GB unified memory, hitting 32 tokens per second using the Lucebox inference engine with DSpark speculative decoding. 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: https://bit.ly/fahd-mirza Coupon code: FahdMirza 🔥 Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza #lucebox #dflash #halostrix #deepseekv4flash PLEASE FOLLOW ME: ▶ LinkedIn: / fahdmirza ▶ YouTube: / @fahdmirza ▶ Blog: https://www.fahdmirza.com RESOURCES: ▶ https://fahdmirza.com All rights reserved © Fahd Mirza

Choose to Build with AI
Matched to DeepSeek V4

AI Maker Residence 3

The third AI workshop taught by our legendary teacher, Nick Sarafa. This is a full-day hands-on training workshop for purposeful co-creation with AI using Claude Code. Imagine having access to hundreds of billions of dollars of computing power and knowing exactly how to make it work for you through the power of super intelligence.

◆ Fri 09 Oct 2026 ◆ KOKO Cafe, London ◆ With Nick Sarafa
Get your seat See every event
AI Maker Residence 3
Live event
AI Maker Residence 3
Fri 09 Oct 2026

More like this

Running one yourself?

List your AI event,
wherever it is.

A meetup, a workshop, a hackathon, a conference. Any city, or online. Tell us about it and it lands in front of people already learning this stuff.

List your AI event