AMD
Radeon RX 9070 GRE
High-performance Radeon RX 9070 GRE graphics card with 12 GB GDDR6 memory
- TDP
- 220 W
- TPP
- 2,194
- FP16
- 34.28 TFLOPS (1:1)
- FP32
- 34.28 TFLOPS
The decision
Where it wins
- High peak performance with up to 274 TFLOPs in 8-bit precision
- Support for advanced video formats and AI accelerators
- Wide range of connectivity options including DisplayPort 2.1a and HDMI 2.1b
Where it doesn't
- High power consumption of 220W typical board power
- Minimum PSU recommendation of 650W
- Limited upgradeability due to soldered memory
Key Features
- ✦12 GB GDDR6 memory
- ✦Up to 2790 MHz game frequency
- ✦432 GB/s memory bandwidth
- ✦96 AI accelerators
- ✦48 ray accelerators
- ✦Wide range of supported video formats
Specifications
Structured product data, grouped by system.
Core hardware09
| GPU Name | Navi 48 |
|---|---|
| Base Clock | 1420 MHz |
| Game Clock | 2220 MHz |
| GPU Variant | Navi 48 XL |
| Architecture | RDNA 4 |
| Chip Package | HFCBGA-2069 |
| Process Type | N4P FinFET |
| Shader Model | 6.9 |
| Stream Processors | 3072 |
Memory & compute15
| Bus Type | PCIe® 5.0 x16 |
|---|---|
| L0 Cache | 32 KB per CU |
| L2 Cache | 6 MB |
| L3 Cache | 48 MB |
| Bandwidth | 432.0 GB/s |
| GPU Memory | 48 MB |
| Memory Bus | 192 bit |
| Memory Size | 12 GB |
| Memory Type | GDDR6 |
| Memory Clock | 2250 MHz |
| Memory Speed | Up to 18 Gbps |
| Infinity Cache | 3rd Gen |
| Max Memory Size | 12 GB |
| Memory Bandwidth | Up to 432 GB/s |
| Memory Interface | 192-bit |
AI & acceleration06
| RT Cores | 48 |
|---|---|
| Boost Clock | 2790 MHz |
| Ray Tracing | 3rd Gen |
| Matrix Cores | 96 |
| Video Core Next | 5.0.0 |
| Display Core Next | 4.0.1 |
Display & media01
| Radiance Display Engine | 2nd Gen |
|---|
Power & thermal05
| TDP | 220 W |
|---|---|
| Suggested PSU | 550 W |
| Power Connectors | 2x 8-pin |
| Minimum PSU Recommendation | 650W |
| Typical Board Power (Desktop) | 220W |
Physical & connectivity05
| Die Size | 357 mm² |
|---|---|
| Slot Width | Dual-slot |
| Connectivity | DisplayPort™ 2.1a, HDMI™ 2.1b |
| Package Size | 45 mm × 35 mm |
| Process Size | 4 nm |
Platform & software02
| OpenGL | 4.6 |
|---|---|
| Vulkan | 1.4 |
Other specifications40
| TPP | 2194 |
|---|---|
| FP16 | 34.28 TFLOPS (1:1) |
| FP32 | 34.28 TFLOPS |
| FP64 | 1.071 TFLOPS (1:32) |
| INT4 | 548.5 TOPS |
| INT8 | 274.3 TOPS |
| ROPs | 96 |
| TMUs | 192 |
| OpenCL | 2.0 |
| Density | 151.0M / mm² |
| DirectX | 12 Ultimate (12_2) |
| Foundry | TSMC |
| Outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1a |
| Features | AMD Software Adrenalin Edition, AMD FSR™ Redstone, AMD Fluid Motion Frames, AMD Radeon™ Super Resolution, AMD Smart Access Memory, AMD Smart Access Video, AMD Radeon™ Boost, AMD Radeon™ Anti-Lag 2, AMD Radeon™ Image Sharpening 2, AMD Enhanced Sync Technology, AMD FreeSync™ Technology, AMD Radeon™ Chill, AMD Virtual Super Resolution |
| Successor | Alpha Trion |
| Generation | Navi IV |
| Pixel Rate | 267.8 GPixel/s |
| Shader ISA | GFX12.0 (gfx1201) |
| JPEG Engine | 5.0.0 |
| Predecessor | Navi III |
| TPP Density | 6.38 |
| Transistors | 53.9 billion |
| Compute Units | 4th Gen |
| Graphics Card | RX 9000 |
| Game Frequency | Up to 2790 MHz |
| AI Accelerators | 96 |
| Graphics/Compute | 12.0.1 |
| Radiance Caching | FSR 0.9.0 (Technical Preview) |
| Ray Accelerators | 48 |
| Ray Regeneration | FSR 1.2.1 |
| Transistor Count | 53.9 B |
| Peak Pixel Fill-Rate | Up to 267.8 GP/s |
| Supported Rendering Format | HDMI™ 4K Support: Yes, 4K H264 Decode: Yes, 4K H264 Encode: Yes, H265/HEVC Decode: Yes, H265/HEVC Encode: Yes, AV1 Decode: Yes, AV1 Encode: Yes |
| Achievability, Frequency, And Sustainability | will vary based on several factors, including but not limited to: thermal conditions and variation in applications and workloads. |
| Peak Half Precision (FP16 Matrix) Performance | 137 TFLOPs |
| Peak Half Precision (FP16 Vector) Performance | 34.3 TFLOPs |
| Peak 4-Bit Precision (INT4 Matrix) Performance | 549 TOPs |
| Peak 8-Bit Precision (INT8 Matrix) Performance | 274 TOPs |
| Peak Single Precision (FP32 Vector) Performance | 34.3 TFLOPs |
| Peak 8-Bit Precision (FP8 Matrix) Performance (E5M2, E4M3) | 274 TFLOPs |
Read the record
- Source on record
- amd.com
The Radeon RX 9070 GRE is a high-end graphics card designed for demanding tasks such as gaming, video editing, and AI workloads. It features a robust set of features and accelerators, including support for advanced video formats and AI processing capabilities. However, the card's high power consumption and minimum PSU requirement of 650W may limit its suitability for systems without adequate power supplies. The trade-off here is between performance and power efficiency, making it ideal for users who prioritize raw performance over power consumption.
Frequently Asked Questions
Who is Radeon RX 9070 GRE for?↓
What are the drawbacks of Radeon RX 9070 GRE?↓
What does Radeon RX 9070 GRE do well?↓
Alternatives to consider
See all alternatives →- Another option Radeon RX 9070
Achievable frequency of up to 2520 MHz
Explore its evidence - Another option Minisforum MS-S1 Max
128GB unified memory in a mini-PC chassis
up to 128 GB LPDDR5x-8000 MT/s with 256 GB/s bandwidthDesign score 9.2/10 - Another option GMKtec EVO-X2 (128GB)
128GB massive memory pool
128GB LPDDR5X 8000MHzDesign score 8.0/10
Further reading
Featured badge
Building this product? Add the badge to your site to show it’s in the index.
<a href="https://fathomlayer.com/compute/local-ai-workstations/radeon-rx-9070-gre" target="_blank" rel="noopener noreferrer"><img src="https://fathomlayer.com/fathom-badge.svg" alt="Featured on Fathom Layer" width="250" height="54" /></a>
