B300
NVIDIA · Blackwell Ultra
288 GBHBM3e
8 TB/sBandwidth
4.5 PFFP8 dense
$4,899 /GPU/mo$6,552 · −25%
AMD · CDNA 4 · OAM · 8-GPU UBB
Rent the AMD Instinct MI355X by the month.
The AMD Instinct MI355X pairs 288 GB of HBM3E with 5.0 PF of dense FP8 and 10.1 PF of FP4, on the CDNA 4 architecture. It matches Blackwell-class throughput with more memory than a B200, for teams running ROCm.
288 GBHBM3E per GPU
8 TB/sMemory bandwidth
5 PFFP8 dense
10.1 PFFP4 dense
Why the MI355X
What the MI355X is best at
- 288 GB HBM3E per GPU. 2.3 TB of HBM on an 8-GPU node.
- 5.0 PF FP8 dense. Blackwell-class FP8 throughput with native FP6 and FP4 support.
- Strong FP64. Keeps double precision for HPC and simulation workloads.
- Memory-bound LLM inference on ROCm
- Training and fine-tuning with PyTorch on ROCm
- HPC and scientific computing
MI355X is liquid-cooled at up to 1,400 W per GPU. ROCm supports PyTorch, JAX, vLLM and SGLang out of the box.
Pricing
MI355X monthly price by server size
One flat price per GPU, the same from 1 to 8 GPUs. The market median is the public on-demand list price of specialist GPU clouds × 730 hours.
| Server | CoreGPU / month | Market median / month | You save / month | You save / year | ≈ per GPU-hour |
|---|---|---|---|---|---|
| 1× MI355X | $2,449 | $836 | $10,032 | $3.35 | |
| 2× MI355X | $4,898 | $1,672 | $20,064 | $3.35 | |
| 4× MI355X | $9,796 | $3,344 | $40,128 | $3.35 | |
| 8× MI355X | $19,592 | $6,688 | $80,256 | $3.35 |
Prices in USD, excluding taxes. Market median checked Nov 4, 2026 across specialist GPU clouds; hyperscalers excluded. All GPU prices
Compare
MI355X vs B300
MI355X has more dense FP8 (5.0 vs 4.5 PF) and the same 288 GB; B300 leads on FP4 (13.5 vs 10.1 PF) and on CUDA-only software.
| MI355X | B300 | |
|---|---|---|
| Architecture | CDNA 4 | Blackwell Ultra |
| GPU memory | 288 GB HBM3E | 288 GB HBM3e |
| Memory bandwidth | 8 TB/s | 8 TB/s |
| FP8 dense | 5 PF | 4.5 PF |
| FP4 dense | 10.1 PF | 13.5 PF |
| Interconnect | Infinity Fabric · 1.08 TB/s | NVLink 5 · 1.8 TB/s |
| Power (TDP) | 1,400 W | 1,100 W |
| Price per GPU / month | $2,449 | $4,899 |
| Price per GB of memory | $8.50 | $17.01 |
| Price per FP8 PFLOPS | $490 | $1,089 |
| Availability | 21 available | Only 9 left |
Specifications
AMD Instinct MI355X technical specs
Per-GPU figures from the vendor datasheet. Tensor throughput is dense (without sparsity).
| Model | AMD Instinct MI355X |
|---|---|
| Architecture | CDNA 4 |
| Form factor | OAM · 8-GPU UBB |
| GPU memory | 288 GB HBM3E |
| Memory bandwidth | 8 TB/s |
| FP8 Tensor (dense) | 5 PF |
| FP4 Tensor (dense) | 10.1 PF |
| Interconnect | Infinity Fabric · 1.08 TB/s |
| Power (TDP) | 1,400 W |
| GPUs per server | 1 to 8 |
| Availability | 21 available |
FAQ
MI355X rental: common questions
Another question? Our engineers answer within one business day.
Contact usHow much does it cost to rent an AMD Instinct MI355X per month?
$2,449 per GPU per month at CoreGPU, about $3.35 per GPU-hour, versus a market median of $3,285 ($4.50/hour × 730 h). A full 8-GPU server is $19,592 per month, taxes excluded.
Is the MI355X available right now?
Yes: 21 available in the current allocation of 64 GPUs. In-stock servers are delivered with root SSH access in under 60 seconds after payment.
How many MI355X GPUs can I rent?
From 1 to 8 GPUs per server, at the same price per GPU. Servers with 8 GPUs come with the full Infinity Fabric mesh. Need more? Rent several servers or ask for a private allocation.
MI355X or B300?
MI355X has more dense FP8 (5.0 vs 4.5 PF) and the same 288 GB; B300 leads on FP4 (13.5 vs 10.1 PF) and on CUDA-only software. See the full MI355X vs B300 comparison.
What do I get with a MI355X server?
Dedicated GPUs (never shared or sliced), root SSH access, your choice of a clean OS or a ready image with ROCm, PyTorch and vLLM, local NVMe scratch, and month-to-month billing with no setup fee.
Alternatives
Other GPUs in stock now
Deploy your MI355X server in under 60 seconds
Pick 1 to 8 GPUs in the configurator above. Month to month, cancel anytime.