llamaperf
Submit

RX 6800 16GB

AMD · 16GB · 1 report

See what fits on this GPU →

Use the calculator to check which models fit in 16 GB of VRAM. The reports below include different GPU counts and memory setups; a model listed here may need extra cards or CPU offloading.

How to compare these reports →
This page is thin (1 of 3 reports needed for indexing). Help fill it in.
LatestMost reportedFastest t/s

Qwen3.8 27B

2× RX 6800 16GB · llama.cpp · 131,072 ctx

reported speed:
45.0 tokens/s generation
quant:
IQ4_XS

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User currently runs llama.cpp on two RTX 2060 12GB cards (24GB total) with Qwen3.8 27B IQ4_XS at 131k context, getting ~45 tok/s. Considering upgrade to RX 6800 16GB + RX 6800 XT 16GB (32GB total) and asks about performance and ROCm/Vulkan support.