AMD Instinct MI300X: specs, pricing and what it can run

The credible non-NVIDIA option: 192GB at 5.3 TB/s. The constraint is software maturity — ROCm support in serving stacks trails CUDA.

Specifications

SpecAMD Instinct MI300X
ArchitectureCDNA 3
Released2023
Memory192 GB HBM3
Memory bandwidth5,300 GB/s
Dense FP161,307 TFLOPS
FP8 tensor coresYes
Board power750 W
InterconnectInfinity Fabric (896 GB/s)
Segmentdatacenter

What fits in 192 GB

Weights only, at 85% of nominal capacity to leave room for the KV cache and activations. Long-context serving needs materially more headroom than this table implies.

QuantisationLargest model (weights only)
FP16~87B parameters
FP8 / INT8~175B parameters
4-bit~350B parameters

Rental cost

Indicative on-demand pricing runs roughly $1.80–$4.50 per GPU-hour depending on provider, region, and commitment. Spot and reserved capacity sit well below that band. These are ranges rather than quotes: street prices move week to week, so check live cloud price feed before budgeting.

Related

Deploy a model with Swfte Connect

One gateway, every provider, per-token cost visibility. Swap models without touching your code.