← AI Hashrate

RTX 4080 Super 16GB vs RTX 5090 32GB for Local LLMs

The RTX 5090 32GB has about 143% more memory bandwidth (1,792 vs 736 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 143% 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 4080 Super 16GB: Mixtral-8x7B-Instruct-v0.1 (46.7B). MSRP is $999 for the RTX 4080 Super 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 44 rows vs 0. Methodology.

Spec comparison

RTX 4080 Super 16GBRTX 5090 32GB
VendorNVIDIANVIDIA
VRAM16 GB32 GB
Memory typeGDDR6XGDDR7
Memory bandwidth736 GB/s1,792 GB/s
TDP320 W575 W
MSRP (list)$999$1,999
BuyASUS ProArt GeForce RTX 4080 Super OC (affiliate) · More listingsSearch 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

ModelParams (B)RTX 4080 Super 16GB tok/sRTX 4080 Super 16GB fitsRTX 5090 32GB tok/sRTX 5090 32GB fitsWinner
Qwen3-0.6B0.8585.5 est.Yes1425.5 est.YesRTX 5090 32GB
gemma-3-1b-it1.0468.4 est.Yes1140.4 est.YesRTX 5090 32GB
Llama-3.2-1B-Instruct1.2390.3 est.Yes950.3 est.YesRTX 5090 32GB
Qwen3-1.7B2.0234.2 est.Yes570.2 est.YesRTX 5090 32GB
Qwen3-Coder-Next79.755.3 est.No538.6 est.NoRTX 5090 32GB
Qwen3-Next-80B-A3B-Instruct81.353.2 est.No518.3 est.NoRTX 5090 32GB
Qwen3-30B-A3B30.5338.0 est.No380.1 est.YesRTX 5090 32GB
Qwen3-Coder-30B-A3B-Instruct30.5338.0 est.No380.1 est.YesRTX 5090 32GB
GLM-4.7-Flash31.2324.5 est.No380.1 est.YesRTX 5090 32GB
Qwen3-30B-A3B-Instruct-250730.5338.0 est.No380.1 est.YesRTX 5090 32GB
Llama-3.2-3B-Instruct3.2146.4 est.Yes356.4 est.YesRTX 5090 32GB
Phi-4-mini-instruct3.8123.3 est.Yes300.1 est.YesRTX 5090 32GB
Phi-4-mini-reasoning3.8123.3 est.Yes300.1 est.YesRTX 5090 32GB
gemma-3-4b-it4.3120.1 est.Yes292.4 est.YesRTX 5090 32GB
Qwen3-4B-Instruct-25074.0117.1 est.Yes285.1 est.YesRTX 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 4080 Super 16GBRTX 5090 32GB
Catalog models that fit25 of 6138 of 61
Largest exclusive fit—Mixtral-8x7B-Instruct-v0.1 (46.7B)

RTX 4080 Super 16GB details → · RTX 5090 32GB details →