hardNewAMDMicrosoftOracle

The MI300X has 192 GB per card. When does AMD actually win against an H100 for LLM serving, and what would you check before betting on it?

192 GB and 5.3 TB/s per card beat the H100 on both memory numbers at a lower hourly price. Whether that wins in production is a question about achieved bandwidth and ROCm kernel coverage, and there is a short list of numbers to run before you sign the order.

Updated Sep 2026 · Grounded in real AI infrastructure interview loops and written to a senior-engineer editorial bar, with every number worked and every diagram hand-built.

more free answers with an account · no card

The concepts behind this question

Ranked by how closely each one overlaps this question's topic, so the first card is the thing to read if the answer above moved too fast.

Advanced

🧩 GPU & Accelerator Architecture🔒 Premium

AMD Instinct and ROCmAMD's Instinct line competes on memory: 192 GB on the MI300X, 256 on the MI325X, 288 on the MI355X, with dense fp8 peaks at or above NVIDIA's at each generation. The catch is software: ROCm and HIP run most PyTorch and the main serving engines, but the attention, MoE and quantization kernels arrive on CUDA first and measured throughput has trailed the spec sheet. Interviewers want the numbers, the wavefront-of-64 difference, and a clear-eyed statement of when the memory argument wins.

Foundational

🧭 Ownership & Judgment

Talking About Cost and Capacity with LeadershipInfrastructure engineers are asked to justify large numbers to people who do not share their vocabulary, and the conversations go wrong in predictable ways: a technical objection with no alternative, a forecast with no assumptions, or a cost quoted in a unit the listener cannot act on. What works is a small number of costed options, a stated recommendation, the decision needed by a date, and every figure expressed in whatever the listener actually controls.

Advanced

🧮 Napkin Math & Capacity🔒 Premium

TCO: Buy vs RentWhether to buy GPUs or rent them is a utilization question dressed as a finance question. An owned H100 costs a few tens of thousands of dollars up front and a known amount per hour in power, cooling, space and operations; a rented one costs a few dollars per hour and nothing when idle. The break-even is the utilization at which the owned hourly cost, amortized over the hardware's useful life, equals the rental rate. This page builds the owned cost from parts, works the break-even, and adds the terms the simple model leaves out: depreciation risk, reserved discounts, and the price of idle capacity.

Foundational

🚀 Inference & Serving

Prefill vs DecodeAn LLM request runs in two phases with opposite hardware profiles: prefill reads the whole prompt in one compute-bound pass and decides time to first token, decode emits one token per forward pass and is bound by memory bandwidth. Every serving decision, from batch size to which GPU to buy to whether to split the two phases across machines, follows from that split.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackWhy are Groq and Cerebras so fast at batch 1, and what does that speed cost at scale?Next in this trackMIG versus MPS: what isolation does each give you when sharing a GPU, and which would you pick for a multi-tenant inference node?Next in this trackYou are moving a model to fp4 inference on Blackwell. What breaks first, and how would you measure whether the result is acceptable?

FEDITOR'S NOTE

Scored on the fit-and-bandwidth derivations that make the capacity argument concrete, the honesty about spec-versus-measured throughput, and a test plan that would settle the question for a specific model.

DISCUSSION · 0

No comments yet — be the first to share your approach.