NVIDIA GeForce RTX 5090
Updated 29 min ago · first seen 11 Sept 2026
hw_01M293SPN8ETMB68N9QZA5J7NJ
- Kind
- gpu
- T2 · 29 min ago
- Memory
- 32 GB GDDR7
- T2 · 29 min ago
- Bandwidth
- 1,792 GB/s
- T2 · 29 min ago
- TDP
- 575 W
- T2 · 29 min ago
- Released
- Jan 2025
- T2 · 29 min ago
Specification
- Release date
- Jan 2025
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Architecture
- Blackwell
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Kind
- gpu
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Manufacturer
- NVIDIA
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Memory bandwidth
- 1,792 GB/s
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Memory
- 32 GB
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Memory type
- GDDR7
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Runtimes
- cuda, vllm, llama.cpp, exllama
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- Spec sheet
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
- TDP
- 575 W
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 29 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
10
Source tiers
T210
Freshest observation
29 min ago
Conflicts
None
Models whose estimated memory footprint fits this device — see estimate method.
No models recorded
- Manufactured by
- NVIDIA
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Release daterelease_date1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Jan 2025 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Architecturearchitecture1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Blackwell | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Kindkind1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| gpu | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Manufacturermanufacturer1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| NVIDIA | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Memory bandwidthmemory_bandwidth_gbs1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 1,792 GB/s | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Memorymemory_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 32 GB | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Memory typememory_type1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| GDDR7 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Runtimesruntimes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| cuda, vllm, llama.cpp, exllama | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Spec sheetspec_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5090/ | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
TDPtdp_watts1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 575 W | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New hardware: NVIDIA GeForce RTX 5090 (NVIDIA)
registry
No documents recorded