What is the biggest model the RX 7900 XT can run?

Gemma 3 27B, which needs about 19 GB, on the 20 GB version at about 26 tok/s.

What is the biggest model the RX 7900 XTX can run?

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

RX 7900 XT vs RX 7900 XTX for local AI

Q: Which is better for local AI, the RX 7900 XT or the RX 7900 XTX?

The RX 7900 XTX: it fits bigger models and runs faster. The RX 7900 XTX fits more: up to Qwen3 32B, against Gemma 3 27B on the RX 7900 XT. The RX 7900 XTX generates about 20% faster on any model both can run, because it has 960 GB/s of memory bandwidth to the RX 7900 XT's 800 GB/s.

The RX 7900 XTX fits more: up to Qwen3 32B, against Gemma 3 27B on the RX 7900 XT. The RX 7900 XTX generates about 20% faster on any model both can run, because it has 960 GB/s of memory bandwidth to the RX 7900 XT's 800 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.

	RX 7900 XT	RX 7900 XTX
Memory	20 GB VRAM	24 GB VRAM
Bandwidth	800 GB/s	960 GB/s
Biggest model that fits	Gemma 3 27B	Qwen3 32B
Best everyday pick	Gemma 3 27B, ~26 tok/s	Qwen3 32B, ~26 tok/s

Model by model

Every model, side by side

Estimated generation speed at the largest memory size each was sold in (20 GB and 24 GB).

Model	RX 7900 XT	RX 7900 XTX
Qwen3 4B About 4 GB	~180 tok/s Runs great	~210 tok/s Runs great
Qwen3 8B About 7 GB	~85 tok/s Runs great	~100 tok/s Runs great
Gemma 3 12B About 10 GB	~54 tok/s Runs great	~65 tok/s Runs great
Qwen3 14B About 11 GB	~47 tok/s Runs great	~57 tok/s Runs great
gpt-oss 20B About 16 GB	~140 tok/s Runs great	~170 tok/s Runs great
Gemma 3 27B About 19 GB	~26 tok/s Usable	~31 tok/s Runs great
Qwen3 30B-A3B About 21 GB	Needs 21 GB	~170 tok/s Runs great
Qwen3 32B About 22 GB	Needs 22 GB	~26 tok/s Usable
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 RX 7900 XTX: 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