NVIDIA A100X

80 GB VRAM312 FP16 TFLOPS300 W TDP0 providers0 offerings0 regions

The NVIDIA A100X is an enterprise-class GPU built on the Ampere architecture, featuring 80 GB of memory with 1,935 GB/s of memory bandwidth and a 300 W TDP. It delivers 19.5 TFLOPS of FP32 performance and 312 TFLOPS of FP16 tensor performance.

Cheapest

—

No current offerings

Median

—

across 0 offerings

Most expensive

—

90-day trend

+38.9%

median rate

Hardware specifications

Same across all providers

Memory

80 GB

HBM2e

What LLMs fit? ↓

FP16 performance

312 TFLOPS

peak

TDP

300 W

Memory bandwidth

1,935 GB/s

Architecture

Ampere

FP32 performance

19.5 TFLOPS

Brand

NVIDIA

Series

A100

Market price history

Median price across all providers

Prices updated 1 hour ago

0 offerings from 0 providers

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

Provider	Count	vCPU	RAM	Region	Per GPU hour	Total/hr	Action
Try broadening your filters or clear all filters to start over.

LLMs that fit on the NVIDIA A100X

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 80 GB per GPU. Showing the 12 largest that fit.

Model	Parameters	16-bit	8-bit	4-bit
Laguna-S 2.1 Poolside	118B 8B active	282 GB Too large	155 GB Too large	90 GB Tight on 1× · 6% spare
gpt-oss-120b OpenAI	117B 5.1B active	— Not released	— Not released	78 GB 1× · 1.7 GB free
Qwen3.6 35B-A3B Alibaba	35B 3B active	86 GB Tight on 1× · 11% spare	47 GB 1× · 33 GB free	28 GB 1× · 52 GB free
Qwen3 32B Alibaba	32.8B	79 GB 1× · 1.4 GB free	43 GB 1× · 37 GB free	25 GB 1× · 55 GB free
Gemma 4 31B Google	31.3B	75 GB 1× · 4.9 GB free	41 GB 1× · 39 GB free	24 GB 1× · 56 GB free
GLM-4.7 Flash Z.ai	31.2B	75 GB 1× · 5.1 GB free	41 GB 1× · 39 GB free	24 GB 1× · 56 GB free
Qwen3.6 27B Alibaba	27.8B	67 GB 1× · 13 GB free	37 GB 1× · 43 GB free	21 GB 1× · 59 GB free
Mistral Small 3.2 24B Mistral AI	24B	58 GB 1× · 22 GB free	32 GB 1× · 48 GB free	18 GB 1× · 62 GB free
gpt-oss-20b OpenAI	21B 3.6B active	— Not released	— Not released	17 GB 1× · 63 GB free
Gemma 3 12B Google	12.2B	29 GB 1× · 51 GB free	16 GB 1× · 64 GB free	9.4 GB 1× · 71 GB free
Granite 4.1 8B IBM	8.8B	21 GB 1× · 59 GB free	12 GB 1× · 68 GB free	6.8 GB 1× · 73 GB free
Qwen3 8B Alibaba	8.2B	20 GB 1× · 60 GB free	11 GB 1× · 69 GB free	6.3 GB 1× · 74 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

Want more from this page?

See incorrect data?

Frequently asked questions

How much VRAM does the A100X have?

The A100X comes with 80 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 A100X?

With 80 GB of VRAM, a single A100X can serve models such as gpt-oss-120b, Qwen3.6 35B-A3B, Qwen3 32B, Gemma 4 31B. 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.