← AI Hashrate

RTX 3090 Ti 24GB vs RTX 4080 Super 16GB for Local LLMs

The RTX 3090 Ti 24GB has about 37% more memory bandwidth (1,008 vs 736 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 37% faster on the RTX 3090 Ti 24GB. The RTX 3090 Ti 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 RTX 3090 Ti 24GB but not the RTX 4080 Super 16GB: GLM-4.7-Flash (31.2B). MSRP is $1,999 for the RTX 3090 Ti 24GB 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 RTX 3090 Ti 24GB posts the higher tok/s in 35 rows vs 9. Methodology.

Spec comparison

RTX 3090 Ti 24GBRTX 4080 Super 16GB
VendorNVIDIANVIDIA
VRAM24 GB16 GB
Memory typeGDDR6XGDDR6X
Memory bandwidth1,008 GB/s736 GB/s
TDP450 W320 W
MSRP (list)$1,999$999
BuySearch 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

ModelParams (B)RTX 3090 Ti 24GB tok/sRTX 3090 Ti 24GB fitsRTX 4080 Super 16GB tok/sRTX 4080 Super 16GB fitsWinner
Qwen3-0.6B0.8801.8 est.Yes585.5 est.YesRTX 3090 Ti 24GB
gemma-3-1b-it1.0641.5 est.Yes468.4 est.YesRTX 3090 Ti 24GB
Llama-3.2-1B-Instruct1.2534.5 est.Yes390.3 est.YesRTX 3090 Ti 24GB
Qwen3-30B-A3B30.5213.8 est.Yes338.0 est.NoRTX 4080 Super 16GB
Qwen3-Coder-30B-A3B-Instruct30.5213.8 est.Yes338.0 est.NoRTX 4080 Super 16GB
Qwen3-30B-A3B-Instruct-250730.5213.8 est.Yes338.0 est.NoRTX 4080 Super 16GB
GLM-4.7-Flash31.2213.8 est.Yes324.5 est.NoRTX 4080 Super 16GB
Qwen3-1.7B2.0320.7 est.Yes234.2 est.YesRTX 3090 Ti 24GB
Llama-3.2-3B-Instruct3.2200.5 est.Yes146.4 est.YesRTX 3090 Ti 24GB
gpt-oss-20b21.5178.2 est.Yes186.5 measuredYesRTX 4080 Super 16GB
Qwen3-Coder-Next79.7170.4 est.No55.3 est.NoRTX 3090 Ti 24GB
Phi-4-mini-instruct3.8168.8 est.Yes123.3 est.YesRTX 3090 Ti 24GB
Phi-4-mini-reasoning3.8168.8 est.Yes123.3 est.YesRTX 3090 Ti 24GB
gemma-3-4b-it4.3164.5 est.Yes120.1 est.YesRTX 3090 Ti 24GB
Qwen3-Next-80B-A3B-Instruct81.3164.0 est.No53.2 est.NoRTX 3090 Ti 24GB

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 3090 Ti 24GBRTX 4080 Super 16GB
Catalog models that fit33 of 6125 of 61
Largest exclusive fitGLM-4.7-Flash (31.2B)—

RTX 3090 Ti 24GB details → · RTX 4080 Super 16GB details →