NVIDIA RTX A6000

Consumer GPU · Ampere

Summary

The RTX A6000 is an Ampere-generation workstation GPU with 48GB of GDDR6. It offers more memory bandwidth than the otherwise similar A40, and supports NVLink for pairing two cards. Its successor is the RTX 6000 Ada.

Launched
2020
VRAM
48 GB
Mem. bandwidth
768 GB/s
On-demand from
Compare prices from 11 providers →

Tech specs

VRAM 48 GB GDDR6
Memory bandwidth 768 GB/s
Interface PCIe
CUDA cores 10,752
Tensor cores 336 (Gen 3)
TDP 300 W
Supported data types
FP64FP32TF32FP16BF16INT8INT4

Cloud rental prices

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

Prices updated

On-demand
$0.50 – $1.09 /GPU/h
Reserved
$0.31 – $1.57 /GPU/h
Spot
$0.39 – $0.56 /GPU/h
Provider On-demand Reserved Spot
AceCloud ? — $0.83 —
Cirrascale ? — $0.90 —
Hyperstack ? $0.50 $0.35 —
Lambda ? $1.09 — —
LeaderGPU ✓ — $0.31 —
Massed Compute ? $0.55 — —
Runpod ✓ $0.59 — —
Seeweb ? $0.83 $0.71 —
Sesterce ✓ $0.63 — —
Vast.ai ✓ $0.87 — $0.56
Verda ? $0.78 $0.72 $0.39
Compare all NVIDIA RTX A6000 cloud providers & configurations →

Models that fit in VRAM

Total VRAM From 16-bit inference 8-bit inference 4-bit inference
1× RTX A6000 48 GB $0.35/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 A6000 96 GB $0.70/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 A6000 144 GB $1.77/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 A6000 192 GB $1.40/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 A6000 240 GB $2.95/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 A6000 288 GB $3.54/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 A6000 336 GB $4.13/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 A6000 384 GB $2.46/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
9× RTX A6000 432 GB $5.31/h DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b DeepSeek-V3.2MiniMax-M2.7gpt-oss-120b
10× RTX A6000 480 GB $5.90/h DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b DeepSeek-V4-ProMiniMax-M2.7gpt-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.