← AI Hashrate

RX 7900 GRE 16GB vs RX 7900 XT 20GB for Local LLMs

The RX 7900 XT 20GB has about 39% more memory bandwidth (800 vs 576 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 39% faster on the RX 7900 XT 20GB. The RX 7900 XT 20GB fits more of the catalog at Q4/8K — 32 vs 25 of 61 models (20 vs 16 GB VRAM). Largest model that fits the RX 7900 XT 20GB but not the RX 7900 GRE 16GB: GLM-4.7-Flash (31.2B). MSRP is $549 for the RX 7900 GRE 16GB vs $899 for the RX 7900 XT 20GB. 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 RX 7900 XT 20GB posts the higher tok/s in 37 rows vs 7. Methodology.

Spec comparison

RX 7900 GRE 16GBRX 7900 XT 20GB
VendorAMDAMD
VRAM16 GB20 GB
Memory typeGDDR6GDDR6
Memory bandwidth576 GB/s800 GB/s
TDP260 W315 W
MSRP (list)$549$899
BuySearch Amazon (affiliate)Search 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)RX 7900 GRE 16GB tok/sRX 7900 GRE 16GB fitsRX 7900 XT 20GB tok/sRX 7900 XT 20GB fitsWinner
Qwen3-0.6B0.8458.2 est.Yes636.4 est.YesRX 7900 XT 20GB
gemma-3-1b-it1.0366.5 est.Yes509.1 est.YesRX 7900 XT 20GB
Llama-3.2-1B-Instruct1.2305.5 est.Yes424.2 est.YesRX 7900 XT 20GB
Qwen3-30B-A3B30.5264.5 est.No169.7 est.YesRX 7900 GRE 16GB
Qwen3-Coder-30B-A3B-Instruct30.5264.5 est.No169.7 est.YesRX 7900 GRE 16GB
Qwen3-30B-A3B-Instruct-250730.5264.5 est.No169.7 est.YesRX 7900 GRE 16GB
Qwen3-1.7B2.0183.3 est.Yes254.5 est.YesRX 7900 XT 20GB
GLM-4.7-Flash31.2253.9 est.No169.7 est.YesRX 7900 GRE 16GB
gpt-oss-20b21.5101.8 est.Yes141.4 est.YesRX 7900 XT 20GB
Phi-4-mini-instruct3.896.5 est.Yes134.0 est.YesRX 7900 XT 20GB
Phi-4-mini-reasoning3.896.5 est.Yes134.0 est.YesRX 7900 XT 20GB
Llama-3.2-3B-Instruct3.2114.5 est.Yes131.2 measuredYesRX 7900 XT 20GB
gemma-3-4b-it4.394.0 est.Yes130.5 est.YesRX 7900 XT 20GB
Qwen3-4B-Instruct-25074.091.6 est.Yes127.3 est.YesRX 7900 XT 20GB
Qwen3-4B-Thinking-25074.091.6 est.Yes127.3 est.YesRX 7900 XT 20GB

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

RX 7900 GRE 16GBRX 7900 XT 20GB
Catalog models that fit25 of 6132 of 61
Largest exclusive fitGLM-4.7-Flash (31.2B)

RX 7900 GRE 16GB details → · RX 7900 XT 20GB details →