← AI Hashrate

RTX 4080 Super 16GB vs RX 7900 GRE 16GB for Local LLMs

The RTX 4080 Super 16GB has about 28% more memory bandwidth (736 vs 576 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 28% faster on the RTX 4080 Super 16GB. Both fit the same number of catalog models at Q4/8K (25 of 61; 16 vs 16 GB VRAM). MSRP is $999 for the RTX 4080 Super 16GB vs $549 for the RX 7900 GRE 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 4080 Super 16GB posts the higher tok/s in 44 rows vs 0. Methodology.

Spec comparison

RTX 4080 Super 16GBRX 7900 GRE 16GB
VendorNVIDIAAMD
VRAM16 GB16 GB
Memory typeGDDR6XGDDR6
Memory bandwidth736 GB/s576 GB/s
TDP320 W260 W
MSRP (list)$999$549
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 fitsRX 7900 GRE 16GB tok/sRX 7900 GRE 16GB fitsWinner
Qwen3-0.6B0.8585.5 est.Yes458.2 est.YesRTX 4080 Super 16GB
gemma-3-1b-it1.0468.4 est.Yes366.5 est.YesRTX 4080 Super 16GB
Llama-3.2-1B-Instruct1.2390.3 est.Yes305.5 est.YesRTX 4080 Super 16GB
Qwen3-30B-A3B30.5338.0 est.No264.5 est.NoRTX 4080 Super 16GB
Qwen3-Coder-30B-A3B-Instruct30.5338.0 est.No264.5 est.NoRTX 4080 Super 16GB
Qwen3-30B-A3B-Instruct-250730.5338.0 est.No264.5 est.NoRTX 4080 Super 16GB
GLM-4.7-Flash31.2324.5 est.No253.9 est.NoRTX 4080 Super 16GB
Qwen3-1.7B2.0234.2 est.Yes183.3 est.YesRTX 4080 Super 16GB
gpt-oss-20b21.5186.5 measuredYes101.8 est.YesRTX 4080 Super 16GB
Llama-3.2-3B-Instruct3.2146.4 est.Yes114.5 est.YesRTX 4080 Super 16GB
Phi-4-mini-instruct3.8123.3 est.Yes96.5 est.YesRTX 4080 Super 16GB
Phi-4-mini-reasoning3.8123.3 est.Yes96.5 est.YesRTX 4080 Super 16GB
gemma-3-4b-it4.3120.1 est.Yes94.0 est.YesRTX 4080 Super 16GB
Qwen3-4B-Instruct-25074.0117.1 est.Yes91.6 est.YesRTX 4080 Super 16GB
Qwen3-4B-Thinking-25074.0117.1 est.Yes91.6 est.YesRTX 4080 Super 16GB

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 16GBRX 7900 GRE 16GB
Catalog models that fit25 of 6125 of 61
Largest exclusive fit——

RTX 4080 Super 16GB details → · RX 7900 GRE 16GB details →