RunLocalAI
amd
GPU
192GB VRAM
workstation

AMD Instinct MI300X

192GB HBM3 datacenter card. Used by Microsoft, Oracle, Meta cloud deployments.

Released 2023

Overview

192GB HBM3 datacenter card. Used by Microsoft, Oracle, Meta cloud deployments.

Specs

VRAM192 GB
Power draw750 W
Released2023
MSRP$15000
Backends
ROCm

Models that fit

Open-weight models small enough to run on AMD Instinct MI300X with usable context.

Llama 3.1 8B Instruct
8B · llama
Llama 4 Scout
109B · llama
Qwen 3 30B-A3B
30B · qwen
Qwen 2.5 Coder 32B Instruct
32B · qwen
Llama 3.3 70B Instruct
70B · llama
Qwen 3 32B
32B · qwen
Gemma 4 31B Dense
31B · gemma
Qwen 3 8B
8B · qwen

Frequently asked

What models can AMD Instinct MI300X run?

With 192GB VRAM, the AMD Instinct MI300X runs 70B models in 4-bit quantization, plus everything smaller. See the model list below for tested combinations.

Does AMD Instinct MI300X support CUDA?

No — AMD Instinct MI300X 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.