How to Run DeepSeek R1 Distilled Reasoning Models on RyzenAI and Radeon GPUs

Re:How to Run DeepSeek R1 Distilled Reasoning Models on Ryze... by larntz on Saturday February 01, 2025 @08:24PM (#42904598)

I wrote a similar post about a week ago, but for an [unsupported] Radeon RX 5500 with 4Gi RAM with ollama and fedora 41. Can only run llama:3.2 or deepseek-r1:1.5b, but they're pretty usable if you're ok with a small model and it's for personal use.

I didn't go into detail about how to setup openweb-ui, but there is documentation for the on the project's site.

https://blue42.net/linux-ollama-radeon-rx5500/post/

[ Parent | on HN ]

Re:How to Run DeepSeek R1 Distilled Reasoning Models on Ryze... by saelthavron on Saturday February 01, 2025 @11:53PM (#42905941)

You have a typo in your ollama.service:

Environmetn="ROCR_VISIBLE_DEVICES=1"

The 't' and 'n' are transposed.

[ Parent | on HN ]

Re:How to Run DeepSeek R1 Distilled Reasoning Models on Ryze... by tarasglek on Sunday February 02, 2025 @03:28AM (#42907128)

Great blog

[ Parent | on HN ]