NVIDIA RTX A4000

Consumer GPU · Ampere

Summary

The RTX A4000 is an Ampere-generation workstation GPU with 16GB of GDDR6. Its larger sibling is the RTX A5000, and it has largely been superseded for cloud workloads by newer Ada-generation cards.

Launched
2022
VRAM
16 GB
Mem. bandwidth
448 GB/s
On-demand from
$0.15 /GPU/h
Compare prices from 4 providers →

Tech specs

VRAM 16 GB GDDR6
Memory bandwidth 448 GB/s
Interface PCIe
CUDA cores 6,144
Tensor cores 192 (Gen 3)
TDP 140 W
Supported data types
FP64FP32TF32FP16BF16INT8INT4

Cloud rental prices

4 providers · available in 3 countries · lowest price per GPU, per hour

Prices updated

On-demand
$0.15 – $0.88 /GPU/h
Reserved
$0.11 – $0.34 /GPU/h
Provider On-demand Reserved Spot
Cirrascale ? — $0.27 —
Hyperstack ? $0.15 $0.11 —
Runpod ⚠️ $0.25 — —
Sesterce ✓ $0.17 — —
Compare all NVIDIA RTX A4000 cloud providers & configurations →

Models that fit in VRAM

Total VRAM From 16-bit inference 8-bit inference 4-bit inference
1× RTX A4000 16 GB $0.11/h Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16 Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16 gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini
2× RTX A4000 32 GB $0.22/h Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16 gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
3× RTX A4000 48 GB $0.75/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
4× RTX A4000 64 GB $0.44/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 GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
5× RTX A4000 80 GB $1.25/h GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 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
6× RTX A4000 96 GB $1.50/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
7× RTX A4000 112 GB $1.75/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
8× RTX A4000 128 GB $0.88/h GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16
10× RTX A4000 160 GB $1.10/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

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

Resources

Detailed documentation from the manufacturer.

Datasheet ↗ Official spec sheet Product page ↗ Manufacturer overview