What is the largest LLM the NVIDIA RTX 2080 Ti can run?

Qwen3 14B, at Q4_K_M using about 10.9 GB of the 11 GB available, at roughly 41 tokens per second (8K context).

How many local AI models run well on the NVIDIA RTX 2080 Ti?

22 of the 69 models we track run fully in its 11 GB of VRAM at Q4_K_M or better.

Generation speed follows memory bandwidth. With 616 GB/s, expect about 43 tokens per second on an 8B model.

Every model we track, checked against the NVIDIA RTX 2080 Ti at 8K context. The largest that runs well is Qwen3 14B.

VRAM11 GBNVIDIA

Bandwidth616GB/s

Runs well22/69models at Q4_K_M or better

Fastest model~274tok/s · gpt-oss 20B

Bars show memory used out of 11 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.