AMD · CDNA 4 · Layer 2
AMD Instinct MI350X
The volume part of the MI350 generation, with the same 288 GB memory advantage.
rent Rentable by the hour from multiple clouds; purchasable at scale.
Specifications
- Memory
- 288 GB HBM3E
- Bandwidth
- 8 TB/s
- Compute
- FP4/FP8; below MI355X
- Power
- Not consistently published
- Interconnect
- Infinity Fabric
- Software
- ROCm
- Form factor
- accelerator
- Workload
- both
Verified 2026-09-06. Fields reading “not published” are exactly that — we do not estimate a figure a vendor withholds.
The catch
Same ROCm question as the MI355X. Check that your serving stack — vLLM, SGLang, TensorRT-LLM — actually supports your model on ROCm before committing.
The economics
AMD claims 2.6x the inference throughput of an H100 on Llama 3.1 405B.
Cost per million tokens is the metric that decides most real purchases, and there is no neutral benchmark for it — every published figure comes from a company selling one side of the comparison. Read all of them, ours included, as claims rather than measurements.
The power question underneath this
A rack of frontier accelerators draws 120–200 kW against a 2026 average of about 27 kW, and the US grid interconnection queue exceeds 2,600 GW with waits approaching five years. Whether you can energise this part is now a harder question than whether you can buy it.
Layer 1 — Energy · The interconnection queue · Rack power density · Tokens per watt
Compared against
- AMD Instinct MI350X vs AMD Instinct MI355X — Same 288 GB, same generation. The question is whether the flagship's extra compute changes your cost per token at all.Compare with AMD Instinct MI355X
Related silicon
- AMD Instinct MI300X — 192 GB HBM3, rent
- AMD Instinct MI355X — 288 GB HBM3E, rent
- NVIDIA B200 — 192 GB HBM3E, rent
- NVIDIA GB200 NVL72 — 13.5 TB HBM3E across the rack, rent
- NVIDIA GB300 NVL72 — Higher HBM3E capacity than GB200; per-rack figure not consistently published, rent
- NVIDIA H100 — 80 GB HBM3, rent