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

Stop watching · start building
Matched to DeepSeek V4

Makers residency 4th edition

Your idea can be anything. At our last workshops, people built plant-based nutrition businesses, a way to measure planetary resilience, crochet headwear and a way to connect lonely people living in the same building. An asset manager went on to raise an additional £25M on their fund within nine months. The fourth workshop is a full day at KOKO with Nick Sarafa, learning to build with Claude Code. Bring the thing you keep meaning to start. We’ll bring the pizza.

◆ Fri 13 Nov 2026 ◆ KOKO, London
Get tickets See every event
Makers residency 4th edition
Live event
Makers residency 4th edition
Fri 13 Nov 2026
Find a job · 6 live roles

Jobs in AI.
Apply now.

Apply once › get screened › meet the company

See all roles

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