RTX 4080 Super 16GB vs V100 32GB SXM2 for Local LLMs

The V100 32GB SXM2 has about 22% more memory bandwidth (900 vs 736 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 22% faster on the V100 32GB SXM2. 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 4080 Super 16GB: Qwen3.6-35B-A3B-FP8 (36.0B). MSRP is $999 for the RTX 4080 Super 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 V100 32GB SXM2 posts the higher tok/s in 44 rows vs 5. Methodology.

Spec comparison

	RTX 4080 Super 16GB	V100 32GB SXM2
Vendor	NVIDIA	NVIDIA
VRAM	16 GB	32 GB
Memory type	GDDR6X	HBM2
Memory bandwidth	736 GB/s	900 GB/s
TDP	320 W	300 W
MSRP (list)	$999	$10,000
Buy	ASUS ProArt GeForce RTX 4080 Super OC · 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 4080 Super 16GB tok/s	RTX 4080 Super 16GB fits	V100 32GB SXM2 tok/s	V100 32GB SXM2 fits	Winner
MiniCPM5-1B	1.08	722.2 est.	Yes	895.6 est.	Yes	V100 32GB SXM2
Qwen3.5-2B	2.0	390.0 est.	Yes	483.6 est.	Yes	V100 32GB SXM2
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	339.1 est.	Yes	420.5 est.	Yes	V100 32GB SXM2
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	354.9 est.	No	322.4 est.	Yes	RTX 4080 Super 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	331.5 est.	No	322.4 est.	Yes	RTX 4080 Super 16GB
Qwen3.6-35B-A3B	36.0	259.1 est.	No	322.4 est.	Yes	V100 32GB SXM2
Qwen3.5-35B-A3B	34.7	277.9 est.	No	322.4 est.	Yes	V100 32GB SXM2
GLM-4.7-Flash	31.2	255.9 est.	No	322.4 est.	Yes	V100 32GB SXM2
Ornith-1.0-35B	35.0	273.3 est.	No	322.4 est.	Yes	V100 32GB SXM2
qwen35b-a3b-fable-sft-abliterated	34.7	265.9 est.	No	322.4 est.	Yes	V100 32GB SXM2
Llama-3.2-3B-Instruct	3.2	243.8 est.	Yes	302.3 est.	Yes	V100 32GB SXM2
gpt-oss-20b	21.5	186.5 measured	Yes	268.7 est.	Yes	V100 32GB SXM2
Qwen3-Coder-Next	79.7	54.8 est.	No	268.3 est.	No	V100 32GB SXM2
Qwen3-Next-80B-A3B-Instruct	81.3	52.7 est.	No	258.2 est.	No	V100 32GB SXM2
gemma-4-26B-A4B-it	25.2	205.3 est.	Yes	254.5 est.	Yes	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 4080 Super 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 4080 Super 16GB details → · V100 32GB SXM2 details →