← All GPUs
GeForce RTX 5090
NVIDIA · Consumer GPU · 2025
Check Latest Price
$1,999 MSRP
Check Price on Amazon →
We earn a commission from qualifying purchases · Prices may vary
Price checked Jul 23, 2026
Performance Benchmarks
Image Generation all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
FLUX.1-dev
BF16 ~26GB VRAM used; community + Spheron internal testing (approximate) |
images per minute |
5.5
img/min
est Diffusers · 2026-05-03
|
Estimated Spheron GPU Benchmark Blog ↗ |
| SDXL Turbo FP16 | images per minute |
120
img/min
ComfyUI · 2025-06-01
|
Independent benchmark Tom's Hardware GPU Benchmarks 2025 ↗ |
|
Stable Diffusion 1.5
FP16 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.763 s/image |
procyon image overall score |
8,193
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Stable Diffusion 1.5 INT8
INT8 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.394 s/image |
procyon image overall score |
79,272
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Stable Diffusion XL
FP16 Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 5.223 s/image |
procyon image overall score |
7,179
score
UL Procyon AI Image Generation · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
LLM Inference all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
Llama-2-13B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 134.502 tok/s |
procyon text overall score |
6,591
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Llama-3-70B
Q4 32GB VRAM, tight fit — editorial estimate pending article-level source verification |
tokens per second |
42
tok/s
est llama.cpp · 2025-06-01
|
Estimated Tom's Hardware GPU Benchmarks 2025 ↗ |
|
Llama-3-8B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 214.285 tok/s |
procyon text overall score |
6,104
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Llama-3.1-8B
FP16 Batch-serving throughput, ~18GB VRAM used; community + Spheron internal testing (approximate) |
batch tokens per second |
3,500
tok/s
est vLLM · 2026-05-03
|
Estimated Spheron GPU Benchmark Blog ↗ |
|
Llama-3.1-8B
Q4_K_M Token generation: single user, batch 1, 4k context, mean of 3 runs |
tokens per second |
215
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Llama-3.1-8B
Q4_K_M Prompt processing: 512-token prompt, batch 1, mean of 3 runs |
prompt tokens per second |
9,800
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Mistral-7B
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 255.945 tok/s |
procyon text overall score |
6,267
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Phi-3.5-mini
Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); output rate 314.435 tok/s |
procyon text overall score |
5,749
score
UL Procyon AI Text Generation (TensorRT) · 2025-01-29
|
Independent benchmark StorageReview GPU Reviews ↗ |
|
Qwen3-8B
Q4_K_XL Token generation: 16K context, batch 1, Ubuntu 24.04, on-hardware lab measurement |
tokens per second |
145.3
tok/s
llama.cpp llama-bench, CUDA 12.8 · 2025-12-09
|
Unverified community Hardware Corner LLM GPU Rankings ↗ |
Full Specifications
Vram gb
32 GB
Vram type
GDDR7
Memory bus
512 bit
Memory bandwidth gbps
1792 GB/s
Tdp watts
575 W
Cuda cores
21760
Pcie interface
PCIe 5.0 x16
Architecture
Blackwell
Related GPUs
Common Questions
Can the GeForce RTX 5090 run local LLMs?
Yes, if the model fits in its 32 GB of memory — VRAM capacity decides which models load at all, while its 1792 GB/s of bandwidth decides how fast tokens generate. With 24 GB or more it can hold large quantized models such as 70B-class LLMs in reduced precision, and our model pages list exact VRAM fits per model.
How much VRAM does the GeForce RTX 5090 have?
GeForce RTX 5090 has 32 GB of video memory with 1792 GB/s of memory bandwidth and a 575 W TDP , per the specification values in our hardware database.
Is the GeForce RTX 5090 worth it for AI workloads?
At a $1,999 MSRP, its value depends on whether your models fit in 32 GB. Compare its VRAM and bandwidth against your target models with our VRAM calculator, or see how it stacks up in head-to-head comparisons.
Guides & Tools
CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.