NVIDIA RTX 6000 Ada

Consumer GPU · Ada Lovelace

Summary

The RTX 6000 Ada is the Ada-generation successor to the RTX A6000, with the same 48GB of GDDR6 but 25% higher memory bandwidth, and significantly increased processing power. It is a capable workstation card for graphics, rendering and small-scale LLM inference. The closest same-generation data-centre card is the L40S. It is superseded by the newer RTX PRO 6000.

Launched
Q1 2023
VRAM
48 GB
Mem. bandwidth
960 GB/s
On-demand from
Compare prices from 7 providers →

Tech specs

VRAM 48 GB GDDR6
Memory bandwidth 960 GB/s
Interface PCIe
CUDA cores 18,176
Tensor cores 568 (Gen 4)
TDP 300 W
Supported data types
FP64FP32TF32FP16BF16FP8INT8

Cloud rental prices

7 providers · available in 2 countries · lowest price per GPU, per hour

Prices updated

On-demand
$0.79 – $1.57 /GPU/h
Reserved
$0.63 – $1.84 /GPU/h
Spot
$0.70 /GPU/h
Provider On-demand Reserved Spot
AceCloud ? — $1.02 —
DigitalOcean ? $1.57 — —
LeaderGPU ✓ $1.35 $0.63 —
Massed Compute ? $0.79 — —
Runpod ✓ $0.99 — —
Sesterce ✓ $1.07 — —
Verda ? $1.40 $1.29 $0.70
Compare all NVIDIA RTX 6000 Ada cloud providers & configurations →

Models that fit in VRAM

Total VRAM From 16-bit inference 8-bit inference 4-bit inference
1× RTX 6000 Ada 48 GB $0.79/h gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 Qwen3-Coder-NextGLM-4.7-FlashNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
2× RTX 6000 Ada 96 GB $1.58/h GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 Qwen3-Coder-NextGLM-4.7-FlashNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16
3× RTX 6000 Ada 144 GB $2.97/h GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 gpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16GLM-4.5-Air MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
4× RTX 6000 Ada 192 GB $3.16/h Qwen3-Coder-NextGLM-4.7-FlashNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
5× RTX 6000 Ada 240 GB $4.95/h GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
6× RTX 6000 Ada 288 GB $5.94/h gpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16GLM-4.5-Air MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
7× RTX 6000 Ada 336 GB $6.93/h gpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16GLM-4.5-Air MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
8× RTX 6000 Ada 384 GB $5.06/h DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b

Open-weights models that fit in VRAM. Estimated using 🤗 accelerate, plus approximation for up to 8K context.

Resources

Detailed documentation from the manufacturer.