L40S 48GB vs RTX 4080 Super 16GB for Local LLMs

The L40S 48GB has about 17% more memory bandwidth (864 vs 736 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 17% faster on the L40S 48GB. The L40S 48GB fits more of the catalog at Q4/8K — 39 vs 25 of 61 models (48 vs 16 GB VRAM). Largest model that fits the L40S 48GB but not the RTX 4080 Super 16GB: Qwen3-Coder-Next (79.7B). MSRP is $8,000 for the L40S 48GB vs $999 for the RTX 4080 Super 16GB. 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 L40S 48GB posts the higher tok/s in 35 rows vs 9. Methodology.

Spec comparison

	L40S 48GB	RTX 4080 Super 16GB
Vendor	NVIDIA	NVIDIA
VRAM	48 GB	16 GB
Memory type	GDDR6	GDDR6X
Memory bandwidth	864 GB/s	736 GB/s
TDP	350 W	320 W
MSRP (list)	$8,000	$999
Buy	Search Amazon (affiliate)	ASUS ProArt GeForce RTX 4080 Super 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)	L40S 48GB tok/s	L40S 48GB fits	RTX 4080 Super 16GB tok/s	RTX 4080 Super 16GB fits	Winner
Qwen3-0.6B	0.8	687.3 est.	Yes	585.5 est.	Yes	L40S 48GB
Qwen3-Next-80B-A3B-Instruct	81.3	562.3 est.	No	53.2 est.	No	L40S 48GB
gemma-3-1b-it	1.0	549.8 est.	Yes	468.4 est.	Yes	L40S 48GB
Llama-3.2-1B-Instruct	1.2	458.2 est.	Yes	390.3 est.	Yes	L40S 48GB
Qwen3-30B-A3B	30.5	183.3 est.	Yes	338.0 est.	No	RTX 4080 Super 16GB
Qwen3-Coder-30B-A3B-Instruct	30.5	183.3 est.	Yes	338.0 est.	No	RTX 4080 Super 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	183.3 est.	Yes	338.0 est.	No	RTX 4080 Super 16GB
GLM-4.7-Flash	31.2	183.3 est.	Yes	324.5 est.	No	RTX 4080 Super 16GB
Qwen3-1.7B	2.0	274.9 est.	Yes	234.2 est.	Yes	L40S 48GB
gpt-oss-20b	21.5	152.7 est.	Yes	186.5 measured	Yes	RTX 4080 Super 16GB
Qwen3-Coder-Next	79.7	183.3 est.	Yes	55.3 est.	No	L40S 48GB
Llama-3.2-3B-Instruct	3.2	171.8 est.	Yes	146.4 est.	Yes	L40S 48GB
Phi-4-mini-instruct	3.8	144.7 est.	Yes	123.3 est.	Yes	L40S 48GB
Phi-4-mini-reasoning	3.8	144.7 est.	Yes	123.3 est.	Yes	L40S 48GB
gemma-3-4b-it	4.3	141.0 est.	Yes	120.1 est.	Yes	L40S 48GB

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

	L40S 48GB	RTX 4080 Super 16GB
Catalog models that fit	39 of 61	25 of 61
Largest exclusive fit	Qwen3-Coder-Next (79.7B)	—

L40S 48GB details → · RTX 4080 Super 16GB details →