DeepSeek V4 Flash on Strix Halo

Name: DeepSeek V4 Flash Inference on Strix Halo: ds4, Quantizations, Distributed Inference and Benchmarks
Uploaded: 2026-06-15T18:21:12Z
Description: [DeepSeek V4 Flash Inference on Strix Halo: ds4, Quantizations, Distributed Inference and Benchmarks] New episode on running DeepSeek V4 Flash on Strix Halo: the ds4 project, distributed ...

Framework Desktop

kyuz0 June 15, 2026, 6:21pm 1

New episode on running DeepSeek V4 Flash on Strix Halo: the ds4 project, distributed inference, and benchmarks.

5 Likes

Topic		Replies	Views
Ryzen AI "Max" -- not so much? Framework Desktop	23	4412	December 2, 2025
Fast finetuning of LLMs like Gemma-3 on Strix Halo (Framework Dekstop) using Unsloth and distributed multi-node training Framework Desktop	3	438	March 10, 2026
DGX Spark vs. Strix Halo - Initial Impressions Framework Desktop	47	10008	April 2, 2026
AMD Strix Halo (Ryzen AI Max+ 395) GPU LLM Performance Tests Framework Desktop ai	17	23511	September 29, 2025
A homeassistant Whisper / Piper docker-compose designed for use with strix halo Framework Desktop	7	900	January 28, 2026

DeepSeek V4 Flash on Strix Halo

Related topics