MI350X rental price: from $5.49/hr today

MI350X offers: 2 configurations from 2 providers

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

MI350X price history and range

MI350X prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its MI350X page with node sizes, fees and its own history.

MI350X hardware specs

Manufacturer datasheet figures for the MI350X. Source: www.amd.com.

LLM memory estimates for this GPU

These models have an estimated inference footprint within 288 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Models that need more than one MI350X

• Qwen3 Coder 480B A35B at 16-bit needs about 1154 GB with the same context and headroom, so at least 5 cards. The cheapest MI350X node with a published size that holds it: 8× at $49.28/hr (DigitalOcean, $6.16 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• GLM 4.5 at 16-bit needs about 862 GB with the same context and headroom, so at least 3 cards. The cheapest MI350X node with a published size that holds it: 8× at $49.28/hr (DigitalOcean, $6.16 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• GLM 4.6 at 16-bit needs about 858 GB with the same context and headroom, so at least 3 cards. The cheapest MI350X node with a published size that holds it: 8× at $49.28/hr (DigitalOcean, $6.16 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the MI350X, and what to pick instead

Start from memory: your model, its context and your batch must fit in 288 GB (the model-fit table above estimates it). Then the MI350X is the right card unless one of these fits your job better.

• If your workload fits within 256 GB, the MI325X rents from $3.80/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.

Rent or buy the MI350X

We have no confirmed MI350X purchase price from the stores we check; renting starts at $5.49 per GPU-hour. A seller quote entered in the calculator gives the break-even.

Compare MI350X purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

MI350X questions

How much does it cost to rent a MI350X?

The cheapest MI350X rental we have is $5.49 per GPU-hour on RunPod (secure cloud), checked 22 October 2026.

How much VRAM does a MI350X have?

288 GB.

Where is the MI350X cheapest right now?

RunPod has the cheapest checked on-demand rate today at $5.49 per GPU-hour.

GPUs near the MI350X

• MI355X288 GB$5.99/hrcheapest on-demand
• B300288 GB$4.99/hrcheapest on-demand
• MI325X256 GB$3.80/hrcheapest on-demand
• GB300288 GB$12.17/hrcheapest on-demand
• GB200186 GB$8.00/hrcheapest on-demand

Related

All 140 GB+ GPUs · GPUs under $2/hr · Price movers this week · RunPod review