NVIDIA Radeon RX 9070 XT GPU: Specs, VRAM, Price & Benchmarks (2026)
The Radeon RX 9070 XT is a real GPU (launched 2025), but no provider on Aquanode is listing it for rental right now, so there is no live hourly price to quote. Availability changes as providers add and retire hardware; the specs, VRAM and price context below still apply.
How much VRAM does the Radeon RX 9070 XT have?
The Radeon RX 9070 XT has 16GB GDDR6, with 640 GB/s of peak memory bandwidth.
Radeon RX 9070 XT VRAM calculator: check which models fit in its memory at each precision.
All models that fit in 16 GB: the open models whose weights and overhead fit, at native, FP8 and INT4 precision.
What can the Radeon RX 9070 XT run?
Popular open models from small to frontier scale, with the memory each needs and how many Radeon RX 9070 XT cards (16GB GDDR6 each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: ~18.3 GB, 2 GPUs | FP8: ~9.2 GB, 1 GPU | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: ~33 GB, 3 GPUs | FP8: ~16.5 GB, 2 GPUs | INT4: ~8.3 GB, 1 GPU |
| Qwen/Qwen3-32B 32.8B | BF16: ~73.2 GB, 5 GPUs | FP8: ~36.6 GB, 3 GPUs | INT4: ~18.3 GB, 2 GPUs |
| Qwen/Qwen-72B 72.3B | BF16: ~162 GB, 11 GPUs | FP8: ~80.8 GB, 6 GPUs | INT4: ~40.4 GB, 3 GPUs |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: ~256 GB, 16 GPUs | – | INT4: ~128 GB, 8 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: ~765 GB, 48 GPUs | – | INT4: ~383 GB, 24 GPUs |
Estimates: weights at the stated precision plus a flat 20% for KV cache and overhead, at a moderate context length. A dash means the precision is not offered for that model (it is already published at that size). INT4 needs a published quantized checkpoint. Open any model for a per-GPU breakdown, or use the Radeon RX 9070 XT VRAM calculator.
Radeon RX 9070 XT specs
| Architecture | launched 2025 |
| VRAM | 16GB GDDR6 |
| Memory bandwidth | 640 GB/s |
| FP16 / BF16 tensor throughput | 195 TFLOPS (peak, dense) |
| FP8 tensor throughput | 389 TFLOPS (peak, dense) |
| TDP | 304W |
| Form factor | PCIe |
Specs sourced from the vendor's public product page. See the source.
GPU Glossary: What is VRAM?, Tensor Cores, CUDA Cores, TFLOPS
Good for
16GB at 640 GB/s with matrix units for FP16 and FP8: 7-8B models at BF16 with room for context, 13-14B models at INT8, and 20B-class models at INT4. Runs on ROCm.
Not good for
ROCm support on consumer Radeon cards is narrower than CUDA, and some inference engines and quantization kernels only target NVIDIA. 16GB rules out 30B-class models at FP16 or INT8.
Related guides
Other models in the same generation. The full list is in the GPU index.
Related reading: RX 9070 XT for AI, and Consumer GPUs for AI.
Get notified when the price drops
GPU supply moves hourly. Tell us what you're waiting for and we'll email you when a matching offer appears across any provider we track.
