RTX 5080 16GB vs V100 32GB SXM2 for Local LLMs

The RTX 5080 16GB has about 7% more memory bandwidth (960 vs 900 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 7% faster on the RTX 5080 16GB. The V100 32GB SXM2 fits more of the catalog at Q4/8K — 43 vs 25 of 73 models (32 vs 16 GB VRAM). Largest model that fits the V100 32GB SXM2 but not the RTX 5080 16GB: Qwen3.6-35B-A3B-FP8 (36.0B). MSRP is $999 for the RTX 5080 16GB vs $10,000 for the V100 32GB SXM2. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: V100 32GB SXM2 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (49 shared models), the RTX 5080 16GB posts the higher tok/s in 39 rows vs 10. Methodology.

Spec comparison

	RTX 5080 16GB	V100 32GB SXM2
Vendor	NVIDIA	NVIDIA
VRAM	16 GB	32 GB
Memory type	GDDR7	HBM2
Memory bandwidth	960 GB/s	900 GB/s
TDP	360 W	300 W
MSRP (list)	$999	$10,000
Buy	NVIDIA GeForce RTX 5080 Founders Edition · More listings · eBay · Newegg · B&H Photo	—

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 49 shared models

Model	Params (B)	RTX 5080 16GB tok/s	RTX 5080 16GB fits	V100 32GB SXM2 tok/s	V100 32GB SXM2 fits	Winner
MiniCPM5-1B	1.08	955.3 est.	Yes	895.6 est.	Yes	RTX 5080 16GB
Qwen3.5-2B	2.0	515.9 est.	Yes	483.6 est.	Yes	RTX 5080 16GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	462.9 est.	No	322.4 est.	Yes	RTX 5080 16GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	448.6 est.	Yes	420.5 est.	Yes	RTX 5080 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	432.4 est.	No	322.4 est.	Yes	RTX 5080 16GB
Qwen3.5-35B-A3B	34.7	362.4 est.	No	322.4 est.	Yes	RTX 5080 16GB
Ornith-1.0-35B	35.0	356.4 est.	No	322.4 est.	Yes	RTX 5080 16GB
qwen35b-a3b-fable-sft-abliterated	34.7	346.9 est.	No	322.4 est.	Yes	RTX 5080 16GB
Qwen3.6-35B-A3B	36.0	338.0 est.	No	322.4 est.	Yes	RTX 5080 16GB
GLM-4.7-Flash	31.2	333.8 est.	No	322.4 est.	Yes	RTX 5080 16GB
Llama-3.2-3B-Instruct	3.2	322.4 est.	Yes	302.3 est.	Yes	RTX 5080 16GB
gemma-4-26B-A4B-it	25.2	271.5 est.	Yes	254.5 est.	Yes	RTX 5080 16GB
gpt-oss-20b	21.5	204.9 measured	Yes	268.7 est.	Yes	V100 32GB SXM2
Qwen3-Coder-Next	79.7	71.4 est.	No	268.3 est.	No	V100 32GB SXM2
Qwen3-Next-80B-A3B-Instruct	81.3	68.8 est.	No	258.2 est.	No	V100 32GB SXM2

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	V100 32GB SXM2
Catalog models that fit	25 of 73	43 of 73
Largest exclusive fit	—	Qwen3.6-35B-A3B-FP8 (36.0B)

RTX 5080 16GB details → · V100 32GB SXM2 details →