[SUBS]RANK
VIDEOS / DONATO CAPITELLA / CFL3TS7ME5S

DeepSeek V4 Flash Inference on Strix Halo: ds4, Quantizations, Distributed Inference and Benchmarks

Donato Capitella DONATO CAPITELLA · JUL 08, 2026

This YouTube video has 48 000 views and was published Jul 8, 2026 on Donato Capitella. That is 2.7x the channel's average views.

DeepSeek V4 Flash Inference on Strix Halo: ds4, Quantizations, Distributed Inference and Benchmarks ▸ WATCH ON YOUTUBE
Views
48 000
Likes
—
Comments
—
Like rate
—
▸ Vs channel average
+169%
This video is at 2.7x the channel's average views.
LAST 13 UPLOADS · ■ THIS VIDEO
Donato Capitella
Donato Capitella
@donatocapitella · 111K SUBS · 86 VIDEOS
AUDIT →
More from this channel
Running models on 32GB, Muse 30B, Qwen 3.8, New Agentic Benchmarks, Toolbox Updates / Discord Running models on 32GB, Muse 30B, Qwen 3.8, New Agentic Benchmarks, Toolbox Updates / Discord 5 100 VIEWS · 2MO AGO How I Configure the Ryzen AI Halo (Strix Halo) for 10-15% Faster Local Inference How I Configure the Ryzen AI Halo (Strix Halo) for 10-15% Faster Local Inference 39 000 VIEWS · 2MO AGO Building and Running a Deep Research Agent locally on Strix Halo & R9700 AI PRO Building and Running a Deep Research Agent locally on Strix Halo & R9700 AI PRO 21 000 VIEWS · 2MO AGO Channel Update, AMD Advancing AI, Gorgon Halo (192GB), ROCmFPX, LuceBox, Lemonade, Kimi K3, Laguna Channel Update, AMD Advancing AI, Gorgon Halo (192GB), ROCmFPX, LuceBox, Lemonade, Kimi K3, Laguna 5 500 VIEWS · 2MO AGO