RTX 5090
NVIDIA's flagship consumer-market graphics card based on the Blackwell architecture, featuring substantial video memory capacity and compute performance. It represents the current performance ceiling for consumer-grade GPUs and is widely used for gaming as well as local AI inference and training.
Core Facts
The RTX 5090 has 32 GB of VRAM.
The RTX 5090 is a consumer-grade flagship graphics card released in 2025, equipped with 32GB of GDDR7 memory.
In an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.
Timeline (last 90 days)
The RTX 5090 has memory capacity and compute power far exceeding ordinary gaming needs, making it a more cost-effective alternative for small- and medium-scale AI inference tasks or specific training scenarios.
The price of the RTX 5090 in Germany soared from about 3,000 euros at the start of the year to 9,000 euros.
These RTX 5090 graphics cards were not bought by gamers but were reconfigured and sent into server farms.
The price increase of the RTX 5090 is about 200% (i.e., the price has become three times the original).
Bilibili creator Luke's DevLab used a single RTX 5090 to run a stress test of 32 prompt sets on Qwen Image 2.1 locally.
141 submissions and 2,156 files over three weeks, covering 45 graphics cards, from Tesla P40 to RTX 5090.
The top submitter was RTX 4090 (12 submissions), second was RX 6900XT (11), and RTX 5090 had only 10.
AI labs are building data centers at massive scale to grab GPU and memory capacity, pushing up consumer graphics card prices, with the 5090 that originally cost 3000-4000 dollars now selling for nearly 7000-8000 dollars.
A dense 27B model runs at roughly 15 tok/s on an RTX 5090, with some conversation turns taking more than 2 minutes.
Nvidia executive Jeff Fisher denied rumors that the RTX 5090 has been discontinued, acknowledging that production capacity is constrained and that restocking is being coordinated.
40 more timeline events
All Facts (20)
The RTX 5090 has 32 GB of VRAM.
80%VerifiedThe RTX 5090 is a consumer-grade flagship graphics card released in 2025, equipped with 32GB of GDDR7 memory.
75%VerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.
70%VerifiedThis workflow can generate continuous videos up to 60 seconds long on a 12 GB GPU.
65%VerifiedThe RTX 5090 is based on NVIDIA's Blackwell architecture.
65%VerifiedThe RTX 5090's full-load power consumption is as high as 575 W.
65%VerifiedRTX 5080配备16GB GDDR7显存
65%VerifiedRTX A6000基于Ampere架构，搭载10496个CUDA核心与48GB GDDR6显存，带宽768 GB/s，FP32算力38.7 TFLOPS
65%Unverified移动端RTX 5090采用完整的GB203核心，拥有超过10,000个CUDA核心和16GB GDDR7显存，理论算力接近上一代桌面端RTX 4090
80%UnverifiedGPT-OSS 20B在RTX 3090上可达约40 Token/s的生成速度，在RTX 5090上能达到200 Token/s
75%UnverifiedFor small-to-medium models that fit within 32 GB of VRAM, the RTX 5090 leads (approximately 45% on Gemma 4 12B and over 75% on GPT-OSS 20B), but the lead on Qwen 3 27B drops from 47% at Q4 to 23% at Q8.
60%UnverifiedOn the 70-billion-parameter DeepSeek R1 distillation model, because the model overflows the RTX 5090's 32 GB of VRAM, the M5 Ultra is more than 20 times faster than the 5090.
60%UnverifiedThe primary test platform for the Fast H3 workflow is a high-end environment consisting of an RTX 5090 paired with 128GB of memory.
60%UnverifiedThe price of the RTX 5090 in Germany soared from about 3,000 euros at the start of the year to 9,000 euros.
50%UnverifiedThese RTX 5090 graphics cards were not bought by gamers but were reconfigured and sent into server farms.
50%UnverifiedThe price increase of the RTX 5090 is about 200% (i.e., the price has become three times the original).
50%UnverifiedThe RTX 5090 has memory capacity and compute power far exceeding ordinary gaming needs, making it a more cost-effective alternative for small- and medium-scale AI inference tasks or specific training scenarios.
50%Unverified141 submissions and 2,156 files over three weeks, covering 45 graphics cards, from Tesla P40 to RTX 5090.
50%UnverifiedThe top submitter was RTX 4090 (12 submissions), second was RX 6900XT (11), and RTX 5090 had only 10.
50%UnverifiedAI labs are building data centers at massive scale to grab GPU and memory capacity, pushing up consumer graphics card prices, with the 5090 that originally cost 3000-4000 dollars now selling for nearly 7000-8000 dollars.
50%