RunLocalAI
amd
GPU
64GB VRAM
workstation

AMD Instinct MI210

64GB CDNA 2. Lower-power AMD datacenter option.

Released 2022

Overview

64GB CDNA 2. Lower-power AMD datacenter option.

Specs

VRAM64 GB
Power draw300 W
Released2022
MSRP$8500
Backends
ROCm

Models that fit

Open-weight models small enough to run on AMD Instinct MI210 with usable context.

Llama 3.1 8B Instruct
8B · llama
Qwen 3 30B-A3B
30B · qwen
Qwen 2.5 Coder 32B Instruct
32B · qwen
Qwen 3 32B
32B · qwen
Gemma 4 31B Dense
31B · gemma
Qwen 3 8B
8B · qwen
DeepSeek R1 Distill Qwen 32B
32B · deepseek
Gemma 4 26B MoE
26B · gemma

Frequently asked

What models can AMD Instinct MI210 run?

With 64GB VRAM, the AMD Instinct MI210 runs 70B models in 4-bit quantization, plus everything smaller. See the model list below for tested combinations.

Does AMD Instinct MI210 support CUDA?

No — AMD Instinct MI210 is an AMD card. Use ROCm (Linux) or the Vulkan backend in llama.cpp instead. CUDA-only tools won't work.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.