NVIDIA · Consumer / Prosumer · GPU card
NVIDIA GeForce RTX 3090 24GB
Exact RTX 3090 reference specifications and AI deployment guidance, separated from FusionPointAI commercial inventory.
Reference only
Reference only
Verified technical specifications
| Manufacturer | NVIDIA |
|---|---|
| Exact SKU | RTX 3090 |
| Product family | NVIDIA RTX 3090 |
| Architecture | Ampere |
| Generation | GeForce AI Reference |
| Entity type | GPU card |
| Lifecycle | Reference only |
| Launch date | The manufacturer has not published this information. |
| VRAM | 24 GB |
| Memory technology | GDDR6X |
| Memory bandwidth | 936 GB/s |
| Power | 350 W |
| Interface | PCIe x16 |
| Form factor | Consumer · PCIe · Card |
| Interconnect | PCIe |
| MIG / partitioning | Not supported |
| Supported numeric formats | FP64, FP32, TF32, BF16, FP16, INT8, INT4 |
| Software stack | cuda, vllm, sglang, tensorrt-llm |
AI workload suitability
LLM inference
Best suited to smaller checkpoints, compressed models or distributed configurations sized by the recommendation engine.
Fine-tuning and training
Suitable for limited fine-tuning and development when software support, cooling and memory capacity are verified.
Image, video and embeddings
FP16 acceleration supports common generative and vector workloads within the listed VRAM envelope.
Power and cooling
350 W published power requires chassis, airflow and power delivery for this exact form factor.
Multi-GPU use
PCIe is the recorded interconnect path; topology must still be validated at node level.
Software ecosystem
cuda, vllm, sglang, tensorrt-llm
Product timeline
Media gallery
Official manufacturer source
https://www.nvidia.com/en-us/geforce/graphics-cards/compare/?section=compare-specs
Last verified: 2026-08-24