What is the biggest model the RTX 3090 can run?

Qwen3 32B, which needs about 22 GB, on the 24 GB version at about 26 tok/s.

What is the biggest model the RTX 4070 Ti Super can run?

gpt-oss 20B, which needs about 16 GB, on the 16 GB version at about 120 tok/s.

RTX 3090 vs RTX 4070 Ti Super for local AI

Q: Which is better for local AI, the RTX 3090 or the RTX 4070 Ti Super?

The RTX 3090: it fits bigger models and runs faster. The RTX 3090 fits more: up to Qwen3 32B, against gpt-oss 20B on the RTX 4070 Ti Super. The RTX 3090 generates about 39% faster on any model both can run, because it has 936 GB/s of memory bandwidth to the RTX 4070 Ti Super's 672 GB/s.

The RTX 3090 fits more: up to Qwen3 32B, against gpt-oss 20B on the RTX 4070 Ti Super. The RTX 3090 generates about 39% faster on any model both can run, because it has 936 GB/s of memory bandwidth to the RTX 4070 Ti Super's 672 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 3090	RTX 4070 Ti Super
Memory	24 GB VRAM	16 GB VRAM
Bandwidth	936 GB/s	672 GB/s
Biggest model that fits	Qwen3 32B	gpt-oss 20B
Best everyday pick	Qwen3 32B, ~26 tok/s	gpt-oss 20B, ~120 tok/s

Model by model

Every model, side by side

Estimated generation speed at the largest memory size each was sold in (24 GB and 16 GB).

Model	RTX 3090	RTX 4070 Ti Super
Qwen3 4B About 4 GB	~210 tok/s Runs great	~150 tok/s Runs great
Qwen3 8B About 7 GB	~99 tok/s Runs great	~71 tok/s Runs great
Gemma 3 12B About 10 GB	~64 tok/s Runs great	~46 tok/s Runs great
Qwen3 14B About 11 GB	~55 tok/s Runs great	~40 tok/s Runs great
gpt-oss 20B About 16 GB	~160 tok/s Runs great	~120 tok/s Runs great
Gemma 3 27B About 19 GB	~30 tok/s Runs great	Needs 19 GB
Qwen3 30B-A3B About 21 GB	~160 tok/s Runs great	Needs 21 GB
Qwen3 32B About 22 GB	~26 tok/s Usable	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?

The RTX 3090: it fits bigger models and runs faster. 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