NVIDIA RTX 3090

Consumer GPU · Ampere

Summary

The flagship gaming GPU of NVIDIA's Ampere generation. Succeeded by the RTX 4090 and RTX 5090. The RTX 3090 was the last of these gaming GPUs to support fast NVLink interconnect in multi-GPU setups.

Launched
Q3 2020
VRAM
24 GB
Mem. bandwidth
936 GB/s
On-demand from
$0.50 /GPU/h
Compare prices from 2 providers →

Tech specs

VRAM 24 GB GDDR6X
Memory bandwidth 936 GB/s
Interface PCIe
CUDA cores 10,496
Tensor cores 328 (Gen 3)
TDP 350 W
Supported data types
FP64FP32FP16BF16INT8INT4

Cloud rental prices

2 providers · lowest price per GPU, per hour

Prices updated

On-demand
$0.50 – $1.39 /GPU/h
Reserved
$0.20 – $0.48 /GPU/h
Provider On-demand Reserved Spot
LeaderGPU $0.69 $0.20 —
Runpod $0.50 — —
Compare all NVIDIA RTX 3090 cloud providers & configurations →

Models that fit in VRAM

Total VRAM From 16-bit inference 8-bit inference 4-bit inference
1× RTX 3090 24 GB $0.50/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
2× RTX 3090 48 GB $0.55/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
3× RTX 3090 72 GB $1.50/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
4× RTX 3090 96 GB $0.95/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
5× RTX 3090 120 GB $1.11/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
8× RTX 3090 192 GB $1.58/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

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

Peak theoretical performance

INT8 Tensor Core 284.7 TOPS
BF16 Tensor Core 142.3 TFLOPS
FP16 Tensor Core 142.3 TFLOPS
TF32 Tensor Core 35.6 TFLOPS
FP32 35.6 TFLOPS

Performance figures assume no sparsity; in cases where only sparse performance figures are published by the manufacturer, these are halved to give approximate dense performance.

Resources

Detailed documentation from the manufacturer.

Whitepaper ↗ Architecture deep-dive (PDF) Product page ↗ Manufacturer overview

Similar GPUs

Other accelerators you might compare.

NVIDIA RTX 4090 View specs & prices → NVIDIA RTX 5090 View specs & prices →