AMD Instinct MI300X
The MI300X is AMD's flagship AI accelerator with an industry-leading 192GB HBM3 memory. Built on CDNA 3 architecture, it targets large language model training and inference workloads.
VRAM
192 GB
Memory
HBM3
Bandwidth
5,300 GB/s
FP16
1,307 TF
TDP
750 W
Memory and compute
Architecture and power
Notes
Flagship AI accelerator with 192GB HBM3. Competes with NVIDIA H100.
Models that may fit on AMD Instinct MI300X
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
More GPUs by AMD
The manufacturer's other cards in the catalog, largest memory first, with bandwidth and power where published.
Frequently asked questions about AMD Instinct MI300X
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
AMD Instinct MI300X has 192 GB of HBM3 at 5,300 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 153B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Gemma 4 31B IT, Llama 3.2 90B Vision, Llama Nemotron Embed Vl 1B V2 and GLM Z1 9B 0414 fit on a single AMD Instinct MI300X with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
5,300 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 153B model at INT8 could be read on the order of 35 times a second on one card, before batching and framework efficiency.
AMD Instinct MI300X has a TDP of 750 W, with a maximum of 750 W, in the OAM form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
AMD Instinct MI300X is a datacenter accelerator, meant for servers and multi-GPU serving, built on the CDNA 3 architecture and released in 2023. It supports a multi-GPU interconnect at 896 GB/s, so a model larger than one card can be split across several.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jan 27, 2026 · Last updated Apr 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.