NVIDIA A100 80GB — Local LLM Performance & Compatibility

The datacenter workhorse of the 2021–2023 AI wave, now the value pick for on-prem business inference: 80 GB HBM2e at 1.9 TB/s runs Llama 3.3 70B at Q4 entirely on one card. No official MSRP — single-unit street pricing has fallen well below launch levels as H100/B200 fleets displace it, and the used/refurb market is active. PCIe version shown; SXM needs an HGX carrier board.

Technical Specifications

VRAM80 GB
Memory Bandwidth1935 GB/s
TDP300 W
ArchitectureAmpere GA100
Release Year2021
MSRP at Launch$15,000
Inference Speed (Llama 3.1 8B Q4_K_M)~145 tokens/sec
Inference Speed (Llama 3.3 70B Q4_K_M)~30 tokens/sec
联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
NVIDIA A100 80GB PCIe
首发建议零售价:$15,000
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

LLMs Compatible with 80 GB VRAM

All models below run comfortably in 80 GB VRAM with Q4_K_M quantization.

Llama 467 GB VRAM · Q4_K_M · ollama run llama4:scout
Llama 3.343 GB VRAM · Q2_K_XS (Tight) · ollama run llama3.3
Llama 3.1 Family6 GB VRAM · Q4_K_M · ollama run llama3.1
DeepSeek R120 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b
Qwen 380 GB VRAM · Q4_K_M · ollama run qwen3:235b-a22b
Qwen 3.574 GB VRAM · Q4_K_M · ollama run qwen3.5:122b
Qwen 3.622 GB VRAM · Q4_K_M · ollama run qwen3.6:35b-a3b
Gemma 317 GB VRAM · Q4_K_M · ollama run gemma3:27b

Best Use Cases

Quick Start with Ollama

Install Ollama then run the recommended model for this GPU:

ollama run llama3.3:70b

FAQ

Can the NVIDIA A100 80GB run local LLMs?

Yes — the NVIDIA A100 80GB has 80 GB VRAM and runs The datacenter workhorse of the 2021–2023 AI wave, now the value pick for on-prem business inference: 80 GB HBM2e at 1.9

How fast is the NVIDIA A100 80GB for AI inference?

The NVIDIA A100 80GB runs Llama 3.1 8B at ~145 tokens/sec with Q4_K_M quantization. For the 70B model it achieves ~30 tokens/sec.

What LLMs can I run on 80 GB VRAM?

With 80 GB you can run: Llama 4, Llama 3.3, Llama 3.1 Family, DeepSeek R1, Qwen 3. Use Ollama for the easiest setup: ollama run llama3.3:70b.

Can I Run It? — NVIDIA A100 80GB

Compare Similar GPUs

VRAM Tier

Buying Guide

← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?