AMD Instinct MI250X
The MI250X features dual Graphics Compute Dies (GCDs) with 128GB HBM2e memory on CDNA 2 architecture. Powers the Frontier supercomputer and excels at HPC and AI training.
VRAM
128 GB
Memory
HBM2e
Bandwidth
3,277 GB/s
FP16
383 TF
TDP
560 W
Memory and compute
Architecture and power
Notes
Dual-GCD design for HPC workloads. Powers Frontier supercomputer.
Models that may fit on AMD Instinct MI250X
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 MI250X
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
AMD Instinct MI250X has 128 GB of HBM2e at 3,277 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 102B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Llama 3.2 90B Vision, Gemma 4 31B IT, Llama Nemotron Embed Vl 1B V2 and GLM Z1 9B 0414 fit on a single AMD Instinct MI250X 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.
3,277 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 102B model at INT8 could be read on the order of 32 times a second on one card, before batching and framework efficiency.
AMD Instinct MI250X has a TDP of 560 W, with a maximum of 560 W, in the OAM form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
AMD Instinct MI250X is a datacenter accelerator, meant for servers and multi-GPU serving, built on the CDNA 2 architecture and released in 2021. It supports a multi-GPU interconnect at 800 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.