What is the biggest model the RTX 5060 Ti can run?

gpt-oss 20B, which needs about 16 GB, on the 16 GB version at about 78 tok/s.

What is the biggest model the RTX 3080 Laptop can run?

gpt-oss 20B, which needs about 16 GB, on the 16 GB version at about 78 tok/s.

RTX 5060 Ti vs RTX 3080 Laptop for local AI

Q: Which is better for local AI, the RTX 5060 Ti or the RTX 3080 Laptop?

They're close for local AI, so pick on price. Both fit the same models we track, up to gpt-oss 20B. They generate at about the same speed, since their memory bandwidth is close (448 and 448 GB/s).

Both fit the same models we track, up to gpt-oss 20B. They generate at about the same speed, since their memory bandwidth is close (448 and 448 GB/s).

The numbers that matter

Memory and bandwidth

Memory decides which models fit. Bandwidth decides how fast they generate, because every token reads the model's active weights once.

	RTX 5060 Ti	RTX 3080 Laptop
Memory	8 or 16 GB VRAM	8 or 16 GB VRAM
Bandwidth	448 GB/s	448 GB/s
Biggest model that fits	gpt-oss 20B	gpt-oss 20B
Best everyday pick	gpt-oss 20B, ~78 tok/s	gpt-oss 20B, ~78 tok/s

Model by model

Every model, side by side

Estimated generation speed at the largest memory size each was sold in (16 GB and 16 GB).

Model	RTX 5060 Ti	RTX 3080 Laptop
Qwen3 4B About 4 GB	~99 tok/s Runs great	~99 tok/s Runs great
Qwen3 8B About 7 GB	~47 tok/s Runs great	~47 tok/s Runs great
Gemma 3 12B About 10 GB	~30 tok/s Runs great	~30 tok/s Runs great
Qwen3 14B About 11 GB	~26 tok/s Usable	~26 tok/s Usable
gpt-oss 20B About 16 GB	~78 tok/s Runs great	~78 tok/s Runs great
Gemma 3 27B About 19 GB	Needs 19 GB	Needs 19 GB
Qwen3 30B-A3B About 21 GB	Needs 21 GB	Needs 21 GB
Qwen3 32B About 22 GB	Needs 22 GB	Needs 22 GB
Llama 3.3 70B About 45 GB	Needs 45 GB	Needs 45 GB
gpt-oss 120B About 67 GB	Needs 67 GB	Needs 67 GB
Qwen3 235B-A22B About 144 GB	Needs 144 GB	Needs 144 GB
DeepSeek R1 671B About 406 GB	Needs 406 GB	Needs 406 GB

Which should you get?

They're close for local AI, so pick on price. Price matters as much as either number: check used prices on the builds page, where every parts list has a measured or estimated speed.

How we estimate

Both columns use the same formula: memory bandwidth divided by the weights read per token, calibrated on our own rack, with Ollama's default 4-bit sizes. Real results are usually within about a third. Measured either one? Send us the number.

Compare

Other matchups

Every comparison