← Back to GPUs
AMD · RX 6000
AMD Radeon RX 6800 XT
$320$649 MSRP
The RX 6800 XT offers 16GB VRAM with near-6900 XT gaming performance at lower used prices. A strong 1440p/4K gaming card on the used market. Like all AMD consumer GPUs, not suitable for AI due to CUDA dependency in the AI ecosystem.
Best ForBest value used AMD gaming card
VerdictExcellent used gaming value at $320 — but NVIDIA-only if you need AI.
AI
2/10
Gaming
7/10
Specifications
VRAM16GB GDDR6
Memory Bandwidth512 GB/s
Stream Processors4,608
Boost Clock2250 MHz
TDP300W
Power Connector2x 8-pin
Length267mm
Form FactorDual Slot
Release Year2020
AI Capabilities
Capable16GB 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 14BMistral 7BFLUX.1 DevStable Diffusion XLStable Diffusion 3.5 LargeHunyuanVideoCogVideoX-5BMochi 1LTX VideoStable Video DiffusionWan Video 14BCodestral 22BAlphaFold 2ESMFold (ESM-2 15B)ESM-2 3BscGPTRFdiffusionFine-tune Llama 8BTrain SDXL LoRATrain FLUX LoRA
Tight fit (may need CPU offload)
Qwen 2.5 32B (20GB Q4)Qwen 2.5 Coder 32B (20GB Q4)LLaVA 1.6 34B (20GB Q4)
Recommended system RAM for AI: 32GB+ (2x GPU VRAM for model overflow)
Performance Estimates
Estimated tokens/sec for LLM inference based on 512 GB/s memory bandwidth — not hardware benchmarks. Methodology · What is Q4/Q8?
Llama 3.1 8B8B
FP16~10-12 tok/sSlowQwen 2.5 32B32B
Offload~1-3 tok/sVery slowQwen 2.5 14B14B
Q8~12-15 tok/sSlowMistral 7B7B
FP16~11-14 tok/sSlowCodestral 22B22B
Q4~13-17 tok/sSlowQwen 2.5 Coder 32B32B
Offload~1-3 tok/sVery slowPros
- +16GB VRAM at great used prices
- +Near-6900 XT performance
- +Solid 1440p/4K gaming
Cons
- -No CUDA
- -RDNA 2 — no AV1 encoding
- -Weaker ray tracing than NVIDIA
gamingbudget