Back to all offerings

AMD Instinct MI455X

432 GB VRAM0 providers0 offerings0 regions

The AMD Instinct MI455X is an enterprise-class GPU built on the CDNA 5 architecture, featuring 432 GB of memory with 19,600 GB/s of memory bandwidth.

Cheapest
No current offerings
Median
across 0 offerings
Most expensive
90-day trend
Not enough data

Hardware specifications

Same across all providers

Memory
432 GB
What LLMs fit? ↓
Memory bandwidth
19,600 GB/s
Architecture
CDNA 5
Brand
AMD
Series
Instinct MI
AMD Instinct MI455X Price History

No price history available

Price tracking data will appear here once available

Prices updated 6 hours ago

0 offerings from 0 providers

Sorted by price ascending. Compare configurations side-by-side.

ProviderCountvCPURAMRegionPer GPU hourTotal/hrAction
Try broadening your filters or clear all filters to start over.

LLMs that fit on the AMD Instinct MI455X

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 432 GB per GPU. Showing the 12 largest that fit.

ModelParameters16-bit8-bit4-bit
DeepSeek R1
DeepSeek
671B
37B active
Not released
826 GB
Too large
481 GB
Tight on 1× · 7% spare
DeepSeek V4 Flash
DeepSeek
284B
Not released
Not released
192 GB
1× · 240 GB free
Solar Open2 250B
Upstage
250B
15B active
601 GB
Too large
330 GB
1× · 102 GB free
192 GB
1× · 240 GB free
Qwen3 235B-A22B
Alibaba
235B
22B active
564 GB
Too large
310 GB
1× · 122 GB free
181 GB
1× · 251 GB free
Laguna-S 2.1
Poolside
118B
8B active
282 GB
1× · 150 GB free
155 GB
1× · 277 GB free
90 GB
1× · 342 GB free
gpt-oss-120b
OpenAI
117B
5.1B active
Not released
Not released
78 GB
1× · 354 GB free
Qwen3.6 35B-A3B
Alibaba
35B
3B active
86 GB
1× · 346 GB free
47 GB
1× · 385 GB free
28 GB
1× · 404 GB free
Qwen3 32B
Alibaba
32.8B
79 GB
1× · 353 GB free
43 GB
1× · 389 GB free
25 GB
1× · 407 GB free
Gemma 4 31B
Google
31.3B
75 GB
1× · 357 GB free
41 GB
1× · 391 GB free
24 GB
1× · 408 GB free
GLM-4.7 Flash
Z.ai
31.2B
75 GB
1× · 357 GB free
41 GB
1× · 391 GB free
24 GB
1× · 408 GB free
Qwen3.6 27B
Alibaba
27.8B
67 GB
1× · 365 GB free
37 GB
1× · 395 GB free
21 GB
1× · 411 GB free
Mistral Small 3.2 24B
Mistral AI
24B
58 GB
1× · 374 GB free
32 GB
1× · 400 GB free
18 GB
1× · 414 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this · Start from a model instead

Want more from this page?

See incorrect data?

Frequently asked questions

How much VRAM does the Instinct MI455X have?
The Instinct MI455X comes with 432 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Which LLMs can I run on the Instinct MI455X?
With 432 GB of VRAM, a single Instinct MI455X can serve models such as DeepSeek V4 Flash, Solar Open2 250B, Qwen3 235B-A22B, Laguna-S 2.1. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.