Skip to content
Voltarum Local LLM Hardware Guide

AMD Radeon graphics cards for local LLMs

Why choose this family
More memory per euro, including a 32 GB card, with ROCm and Vulkan.
The catch
Software is good with llama.cpp and Ollama, thinner elsewhere.
In this familyMemoryBandwidthLargest popular model at 4-bitPrice
Radeon AI PRO R970032 GB645 GB/sQwen3.6 35B A3B$1,550
RX 7900 XTX24 GB960 GB/sQwen3.6 27B$1,358
RX 9070 XT16 GB645 GB/sgpt-oss-20b$759
RX 9060 XT 16 GB16 GB320 GB/sgpt-oss-20b$349

AMD GPUs

AMD Radeon AI PRO R9700

Memory
32 GB
Bandwidth
645 GB/s

Largest popular model at 4-bit: Qwen3.6 35B A3B

32 GB for about a third of an RTX 5090: the cheapest new 32 GB card.

from $1,550 (typical price)Recommended

AMD GPUs

AMD Radeon RX 7900 XTX

Memory
24 GB
Bandwidth
960 GB/s

Largest popular model at 4-bit: Qwen3.6 27B

24 GB and 960 GB/s: RTX 3090-class memory, bought new.

from $1,358 (typical price)Recommended

AMD GPUs

AMD Radeon RX 9070 XT

Memory
16 GB
Bandwidth
645 GB/s

Largest popular model at 4-bit: gpt-oss-20b

AMD's best gaming card is a solid 16 GB AI card too, with ROCm and Vulkan.

from $759 (typical price)Recommended

AMD GPUs

AMD Radeon RX 9060 XT 16 GB

Memory
16 GB
Bandwidth
320 GB/s

Largest popular model at 4-bit: gpt-oss-20b

The cheapest new 16 GB card. Slow memory, but it holds what an RTX 5060 Ti holds.

from $349 (launch price)Good budget option