What is the largest LLM the AMD Radeon RX 6800 XT can run?

gpt-oss 20B, at Q5_K_M using about 15.7 GB of the 16 GB available, at roughly 120 tokens per second (8K context).

How many local AI models run well on the AMD Radeon RX 6800 XT?

28 of the 69 models we track run fully in its 16 GB of VRAM at Q4_K_M or better.

Generation speed follows memory bandwidth. With 512 GB/s, expect about 36 tokens per second on an 8B model.

Every model we track, checked against the AMD Radeon RX 6800 XT at 8K context. The largest that runs well is gpt-oss 20B.

VRAM16 GBAMD

Bandwidth512GB/s

Runs well28/69models at Q4_K_M or better

Fastest model~273tok/s · Qwen3.6 35B-A3B

Bars show memory used out of 16 GB. Pick a row for the full breakdown.

NameMemory usedBest quantSpeed

NameMemory usedBest quantSpeed

NameMemory usedBest quantSpeed

Run it in the cloud

Rent a cloud GPU by the hour. No upfront cost, stop any time.