datacenter
租用 AMD MI355X.
CDNA 3
288GB VRAM
1400W
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$68.80/hr
Lowest $/hr per GPU
$8.60/hr
Providers
1
Instance shapes
1
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| BM.GPU.MI355X.8 | 8× | — | — | — | $68.80/hr | $8.60/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
What's a cloud instance bundle for the AMD MI355X?
A pre-configured VM that pairs the AMD MI355X with a fixed amount of vCPU, RAM, and SSD on a hyperscaler (AWS, Google Cloud, Azure, Oracle, Vultr, etc.). You pay one hourly rate for the whole bundle; the per-GPU rate on the table is just the bundle price divided by the GPU count. Like raw GPU rental it is on-demand — billed while the instance runs, no subscription — though hyperscalers also sell reserved or committed-use plans that trade a term commitment for a lower rate.
Why is per-GPU pricing on instances different from raw GPU rental rates?
Hyperscaler bundles include managed networking, premium NVMe storage, an SLA, and 24/7 support. P2P marketplaces (Vast.ai, RunPod community, io.net) skip those line items, which is why their raw GPU rates are often 3–10× cheaper. The trade-off is reliability and integration: a hyperscaler instance plugs into your existing VPC, IAM, and observability stack out of the box.
Which hyperscaler is cheapest for the AMD MI355X?
Sort the table by the $/hr per GPU column — the lowest row is the cheapest hyperscaler today. Pricing shifts as providers re-price spot capacity and refresh quotas, so the leader can change week to week. Click Launch on a row to head to that provider's sign-up page (affiliate link, doesn't change the rate you pay).
Can I run my own image or container on these instances?
Yes. All listed hyperscalers expose standard compute APIs — bring your own AMI/image, mount custom volumes, install your own drivers, run any container runtime you like. The bundle just sets the hardware shape; the OS layer is yours to configure.
How do I get the cheapest rate on the AMD MI355X overall?
If you can tolerate a P2P marketplace, the Overview tab's "Where to rent it" table usually has the lowest hourly rate by a wide margin. Use a hyperscaler bundle only when you need managed networking, SLAs, or are already inside that cloud's ecosystem (compliance, data-egress costs, IAM).
AI models
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
Models that run on this GPU.
可在此显卡上进行推理的开放权重模型,列出加载每个模型所需的最少显卡数量和精度。每天根据模型大小和显卡内存计算。 显示 161 个适配模型中最大的 60 个。
?
INT4
Kimi K3
by Moonshot AI
Required GPUs
8× AMD MI355X
VRAM 总量
2304 GB
Parameters
2780B
Context
1M tokens
Qwen3.8 2.4T A95B
by Alibaba (Qwen Team)
Required GPUs
8× AMD MI355X
VRAM 总量
2304 GB
Parameters
2446B
Context
1M tokens
?
INT4
LongCat 2.0
by Meituan
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1776B
Context
1M tokens
DeepSeek V4 Pro 0813
by DeepSeek
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1650B
Context
1M tokens
DeepSeek V4 Pro
by DeepSeek
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1602B
Context
1M tokens
?
INT4
Kimi K2.7 Code
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1027B
Context
262K tokens
?
INT4
Ling-2.6-1T
by Inclusionai
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1025B
Context
262K tokens
?
INT4
Ring-2.6-1T
by Inclusionai
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1025B
Context
256K tokens
MiMo-V2.6-Pro
by Xiaomi
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1024B
Context
1M tokens
MiMo-V2.5-Pro
by Xiaomi
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1023B
Context
1M tokens
?
INT4
Kimi K2.6
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2 0905
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1000B
Context
262K tokens
?
INT4
Kimi K2.5
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2 Thinking
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2
by Moonshot AI
Required GPUs
4× AMD MI355X
VRAM 总量
1152 GB
Parameters
1000B (32B active)
Context
128K tokens
?
INT4
Inkling FP4
by Thinking Machines
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
952B
Context
524K tokens
Muse Spark Open
by Meta AI
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
822B
Context
1M tokens
Hy4 preview
by Tencent
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
780B
Context
1M tokens
DeepSeek V4.1 Flash 1017
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
763B
Context
1M tokens
DeepSeek V4.1 Flash
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
763B
Context
1M tokens
GLM-5
by Zhipu AI
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
754B
Context
205K tokens
GLM-5.1
by Zhipu AI
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
754B
Context
205K tokens
glm-5.3
by Zhipu AI
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
753B
Context
1M tokens
GLM 5.2
by Zhipu AI
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
753B
Context
1M tokens
DeepSeek V3.2
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
689B
Context
131K tokens
DeepSeek V3.1 Terminus
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
689B
Context
164K tokens
DeepSeek V3 0324
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
689B
Context
164K tokens
DeepSeek V3.2 Speciale
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
685B
Context
164K tokens
DeepSeek-V3.1
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
685B
Context
164K tokens
?
INT4
DeepSeek V3.1 Nex N1
by Nex Agi
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B
Context
131K tokens
DeepSeek V3.2 Exp
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B
Context
164K tokens
DeepSeek V3
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B (37B active)
Context
128K tokens
R1 0528
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B
Context
164K tokens
Cogito v2.1 671B
by Deepcogito
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B
Context
128K tokens
DeepSeek R1
by DeepSeek
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
671B (37B active)
Context
128K tokens
Step 5 Preview
by StepFun
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
604B
Context
1M tokens
Nemotron 3 Ultra
by Nvidia
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
550B
Context
1M tokens
?
INT4
Beam 1.0 501B A23B
by Reflection
Required GPUs
2× AMD MI355X
VRAM 总量
576 GB
Parameters
501B
Context
1M tokens
Qwen3 Coder 480B A35B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
480B
Throughput
23 tok/s
Minimax M1 80K
by MiniMax
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
456B
Throughput
25 tok/s
MiniMax-Text-01
by MiniMax
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
456B (46B active)
Throughput
244 tok/s
MiniMax M1
by MiniMax
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
456B
Throughput
25 tok/s
MiniMax M3
by MiniMax
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
427B
Throughput
26 tok/s
ERNIE 4.5 VL 424B A47B
by Baidu
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
424B
Throughput
26 tok/s
Llama 3.1 405B
by Meta AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
405B
Throughput
28 tok/s
?
INT4
Hermes 3 405B Instruct
by Nous Research
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
405B
Throughput
28 tok/s
?
INT4
Hermes 4 405B
by Nous Research
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
405B
Throughput
28 tok/s
Llama 4 Maverick
by Meta AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
402B
Throughput
28 tok/s
Trinity Large Thinking
by Arcee AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
399B
Throughput
28 tok/s
Qwen3.5 397B A17B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
397B
Throughput
28 tok/s
?
INT4
Nex-N2-Pro
by Nex Agi
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
397B
Throughput
28 tok/s
?
INT4
Nex-N2.5-Pro
by Nex Agi
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
397B
Throughput
28 tok/s
Hunyuan-Large
by Tencent
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
389B (52B active)
Throughput
215 tok/s
GLM-4.7
by Zhipu AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
358B
Throughput
31 tok/s
GLM-4.6
by Zhipu AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
357B
Throughput
31 tok/s
GLM-4.5
by Zhipu AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
355B (32B active)
Throughput
350 tok/s
GLM 5.3 Flash
by Zhipu AI
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
321B
Throughput
35 tok/s
MiMo-V2.5
by Xiaomi
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
315B
Throughput
36 tok/s
MiMo-V2.6-Flash
by Xiaomi
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
311B
Throughput
36 tok/s
MiMo-V2-Flash
by Xiaomi
Required GPUs
1× AMD MI355X
VRAM 总量
288 GB
Parameters
310B
Throughput
36 tok/s
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →