RTX 5080 16GB vs RX 7900 XTX 24GB for Local LLMs

Both list the same memory bandwidth (960 GB/s), so per-token decode speed should be similar whenever a model fits both. The RX 7900 XTX 24GB fits more of the catalog at Q4/8K — 33 vs 25 of 61 models (24 vs 16 GB VRAM). Largest model that fits the RX 7900 XTX 24GB but not the RTX 5080 16GB: GLM-4.7-Flash (31.2B). MSRP is $999 for the RTX 5080 16GB vs $999 for the RX 7900 XTX 24GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. In the Q4/8K head-to-head below (44 shared models), the RX 7900 XTX 24GB posts the higher tok/s in 12 rows vs 11. Methodology.

Spec comparison

	RTX 5080 16GB	RX 7900 XTX 24GB
Vendor	NVIDIA	AMD
VRAM	16 GB	24 GB
Memory type	GDDR7	GDDR6
Memory bandwidth	960 GB/s	960 GB/s
TDP	360 W	355 W
MSRP (list)	$999	$999
Buy	NVIDIA GeForce RTX 5080 Founders Edition (affiliate) · More listings	ASRock Radeon RX 7900 XTX Phantom Gaming 24GB OC (affiliate) · More listings

MSRP is the launch list price, not live retail. Buy links are Amazon affiliate links — the price after you click is the live price.

Q4 / 8K head-to-head — top 15 of 44 shared models

Model	Params (B)	RTX 5080 16GB tok/s	RTX 5080 16GB fits	RX 7900 XTX 24GB tok/s	RX 7900 XTX 24GB fits	Winner
Qwen3-0.6B	0.8	763.6 est.	Yes	763.6 est.	Yes	Tie
gemma-3-1b-it	1.0	610.9 est.	Yes	610.9 est.	Yes	Tie
Llama-3.2-1B-Instruct	1.2	509.1 est.	Yes	509.1 est.	Yes	Tie
Qwen3-30B-A3B	30.5	440.9 est.	No	203.6 est.	Yes	RTX 5080 16GB
Qwen3-Coder-30B-A3B-Instruct	30.5	440.9 est.	No	203.6 est.	Yes	RTX 5080 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	440.9 est.	No	203.6 est.	Yes	RTX 5080 16GB
GLM-4.7-Flash	31.2	423.2 est.	No	203.6 est.	Yes	RTX 5080 16GB
Qwen3-1.7B	2.0	305.5 est.	Yes	305.5 est.	Yes	Tie
gpt-oss-20b	21.5	204.9 measured	Yes	169.7 est.	Yes	RTX 5080 16GB
Llama-3.2-3B-Instruct	3.2	190.9 est.	Yes	190.9 est.	Yes	Tie
Mistral-7B-Instruct-v0.3	7.2	163.6 measured	Yes	68.0 measured	Yes	RTX 5080 16GB
Qwen3-Coder-Next	79.7	72.1 est.	No	162.3 est.	No	RX 7900 XTX 24GB
Phi-4-mini-instruct	3.8	160.8 est.	Yes	160.8 est.	Yes	Tie
Phi-4-mini-reasoning	3.8	160.8 est.	Yes	160.8 est.	Yes	Tie
gemma-3-4b-it	4.3	156.6 est.	Yes	156.6 est.	Yes	Tie

est. = bandwidth-based estimate; measured = curated real benchmark that overrides the estimate. Fits = weights + KV(8K) + 1 GB overhead ≤ 95% of VRAM.

Fit coverage at Q4 / 8K

	RTX 5080 16GB	RX 7900 XTX 24GB
Catalog models that fit	25 of 61	33 of 61
Largest exclusive fit	—	GLM-4.7-Flash (31.2B)

RTX 5080 16GB details → · RX 7900 XTX 24GB details →