← Back to GPUs
AMD · RX 7000
AMD Radeon RX 7900 XT
$700$849 MSRP
The AMD Radeon RX 7900 XT offers 20GB of GDDR6 memory with solid 4K gaming performance. It has been superseded by the RX 9000 series but remains available at discounted prices. A good used market option for gamers, but not recommended for AI workloads due to limited ROCm support.
Best ForDiscounted 4K gaming with 20GB VRAM
VerdictGood value if found on sale — but the 9070 XT is a better buy new.
AI
4/10
Gaming
8/10
Specifications
VRAM20GB GDDR6
Memory Bandwidth800 GB/s
Stream Processors5,376
Boost Clock2400 MHz
TDP315W
Power Connector2x 8-pin
Length276mm
Form FactorDual Slot
Release Year2022
AI Capabilities
Capable20GB VRAM
Runs most popular models with quantization. The minimum for serious AI work.
No CUDA — most AI frameworks run best on NVIDIA. ROCm support is improving but not all models/tools work.
Can run (Q4 quantized)
Llama 3.1 8BQwen 2.5 32BQwen 2.5 14BMistral 7BFLUX.1 DevStable Diffusion XLStable Diffusion 3.5 LargeHunyuanVideoCogVideoX-5BMochi 1LTX VideoStable Video DiffusionWan Video 14BCodestral 22BQwen 2.5 Coder 32BLLaVA 1.6 34BAlphaFold 2ESMFold (ESM-2 15B)ESM-2 3BscGPTRFdiffusionFine-tune Llama 8BTrain SDXL LoRATrain FLUX LoRA
Recommended system RAM for AI: 40GB+ (2x GPU VRAM for model overflow)
Performance Estimates
Estimated tokens/sec for LLM inference based on 800 GB/s memory bandwidth — not hardware benchmarks. Methodology · What is Q4/Q8?
Llama 3.1 8B8B
FP16~18-23 tok/sUsableQwen 2.5 32B32B
Q4~16-20 tok/sUsableQwen 2.5 14B14B
Q8~22-27 tok/sUsableMistral 7B7B
FP16~21-26 tok/sUsableCodestral 22B22B
Q4~25-31 tok/sUsableQwen 2.5 Coder 32B32B
Q4~16-20 tok/sUsablePros
- +20GB VRAM
- +Good 4K gaming
- +Better price than XTX
Cons
- -No CUDA
- -Weaker RT performance
- -Superseded by 9000 series
gaming