vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

Radeon RX 6800 XT

AMD

16GB VRAM · 512 GB/s bandwidth · 41.5 FP16 TFLOPS · 300W TDP

The Radeon RX 6800 XT has 16GB of VRAM with 512 GB/s memory bandwidth and 41.5 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (115 tok/s), Qwen 2.5 7B (60 tok/s), Llama 3.1 8B (57 tok/s). Models larger than ~27B parameters won't fit even at Q4. Electricity cost is approximately $32/month at 300W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable115 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable60 tok/s
Llama 3.1 8B8.0B4 GBcomfortable57 tok/s
Mistral Small 24B24.0B12 GBtight19 tok/s
Gemma 3 27B27.4B14 GBwon't fit
Qwen 2.5 Coder 32B32.5B16 GBwon't fit
Llama 3.3 70B70.6B35 GBwon't fit
Qwen 2.5 72B72.7B36 GBwon't fit
Llama 3.1 405B405B202 GBwon't fit
DeepSeek R1 671B671B336 GBwon't fit

Similar GPUs

GPUVRAMBWTFLOPSTDP
Arc A77016GB512 GB/s39.3225W
Radeon RX 680016GB512 GB/s32.3250W
Radeon RX 6900 XT16GB512 GB/s46.1300W
Radeon PRO W770016GB576 GB/s63.9190W
Quadro RTX 500016GB448 GB/s22.3230W

Compare with another GPU

Select another GPU to compare specs and model performance side by side.

Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0