RTX 5080 16GB vs RTX 5090 32GB for Local LLMs

The RTX 5090 32GB has about 87% more memory bandwidth (1,792 vs 960 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 87% faster on the RTX 5090 32GB. The RTX 5090 32GB fits more of the catalog at Q4/8K — 38 vs 25 of 61 models (32 vs 16 GB VRAM). Largest model that fits the RTX 5090 32GB but not the RTX 5080 16GB: Mixtral-8x7B-Instruct-v0.1 (46.7B). MSRP is $999 for the RTX 5080 16GB vs $1,999 for the RTX 5090 32GB. 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 RTX 5090 32GB posts the higher tok/s in 37 rows vs 7. Methodology.

Spec comparison

	RTX 5080 16GB	RTX 5090 32GB
Vendor	NVIDIA	NVIDIA
VRAM	16 GB	32 GB
Memory type	GDDR7	GDDR7
Memory bandwidth	960 GB/s	1,792 GB/s
TDP	360 W	575 W
MSRP (list)	$999	$1,999
Buy	NVIDIA GeForce RTX 5080 Founders Edition (affiliate) · More listings	Search Amazon (affiliate)

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	RTX 5090 32GB tok/s	RTX 5090 32GB fits	Winner
Qwen3-0.6B	0.8	763.6 est.	Yes	1425.5 est.	Yes	RTX 5090 32GB
gemma-3-1b-it	1.0	610.9 est.	Yes	1140.4 est.	Yes	RTX 5090 32GB
Llama-3.2-1B-Instruct	1.2	509.1 est.	Yes	950.3 est.	Yes	RTX 5090 32GB
Qwen3-1.7B	2.0	305.5 est.	Yes	570.2 est.	Yes	RTX 5090 32GB
Qwen3-Coder-Next	79.7	72.1 est.	No	538.6 est.	No	RTX 5090 32GB
Qwen3-Next-80B-A3B-Instruct	81.3	69.4 est.	No	518.3 est.	No	RTX 5090 32GB
Qwen3-30B-A3B	30.5	440.9 est.	No	380.1 est.	Yes	RTX 5080 16GB
Qwen3-Coder-30B-A3B-Instruct	30.5	440.9 est.	No	380.1 est.	Yes	RTX 5080 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	440.9 est.	No	380.1 est.	Yes	RTX 5080 16GB
GLM-4.7-Flash	31.2	423.2 est.	No	380.1 est.	Yes	RTX 5080 16GB
Llama-3.2-3B-Instruct	3.2	190.9 est.	Yes	356.4 est.	Yes	RTX 5090 32GB
Phi-4-mini-instruct	3.8	160.8 est.	Yes	300.1 est.	Yes	RTX 5090 32GB
Phi-4-mini-reasoning	3.8	160.8 est.	Yes	300.1 est.	Yes	RTX 5090 32GB
gemma-3-4b-it	4.3	156.6 est.	Yes	292.4 est.	Yes	RTX 5090 32GB
Qwen3-4B-Instruct-2507	4.0	152.7 est.	Yes	285.1 est.	Yes	RTX 5090 32GB

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	RTX 5090 32GB
Catalog models that fit	25 of 61	38 of 61
Largest exclusive fit	—	Mixtral-8x7B-Instruct-v0.1 (46.7B)

RTX 5080 16GB details → · RTX 5090 32GB details →