← AI Hashrate

RX 7900 XT 20GB vs RX 7900 XTX 24GB for Local LLMs

The RX 7900 XTX 24GB has about 20% more memory bandwidth (960 vs 800 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 20% faster on the RX 7900 XTX 24GB. The RX 7900 XTX 24GB fits more of the catalog at Q4/8K — 33 vs 32 of 61 models (24 vs 20 GB VRAM). Largest model that fits the RX 7900 XTX 24GB but not the RX 7900 XT 20GB: gemma-3-27b-it (27.4B). MSRP is $899 for the RX 7900 XT 20GB vs $999 for the RX 7900 XTX 24GB. 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 (46 shared models), the RX 7900 XTX 24GB posts the higher tok/s in 44 rows vs 2. Methodology.

Spec comparison

RX 7900 XT 20GBRX 7900 XTX 24GB
VendorAMDAMD
VRAM20 GB24 GB
Memory typeGDDR6GDDR6
Memory bandwidth800 GB/s960 GB/s
TDP315 W355 W
MSRP (list)$899$999
BuySearch Amazon (affiliate)ASRock Radeon RX 7900 XTX Phantom Gaming 24GB 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 46 shared models

ModelParams (B)RX 7900 XT 20GB tok/sRX 7900 XT 20GB fitsRX 7900 XTX 24GB tok/sRX 7900 XTX 24GB fitsWinner
Qwen3-0.6B0.8636.4 est.Yes763.6 est.YesRX 7900 XTX 24GB
gemma-3-1b-it1.0509.1 est.Yes610.9 est.YesRX 7900 XTX 24GB
Llama-3.2-1B-Instruct1.2424.2 est.Yes509.1 est.YesRX 7900 XTX 24GB
Qwen3-1.7B2.0254.5 est.Yes305.5 est.YesRX 7900 XTX 24GB
Qwen3-30B-A3B30.5169.7 est.Yes203.6 est.YesRX 7900 XTX 24GB
Qwen3-Coder-30B-A3B-Instruct30.5169.7 est.Yes203.6 est.YesRX 7900 XTX 24GB
GLM-4.7-Flash31.2169.7 est.Yes203.6 est.YesRX 7900 XTX 24GB
Qwen3-30B-A3B-Instruct-250730.5169.7 est.Yes203.6 est.YesRX 7900 XTX 24GB
Llama-3.2-3B-Instruct3.2131.2 measuredYes190.9 est.YesRX 7900 XTX 24GB
gpt-oss-20b21.5141.4 est.Yes169.7 est.YesRX 7900 XTX 24GB
Qwen3-Coder-Next79.793.9 est.No162.3 est.NoRX 7900 XTX 24GB
Phi-4-mini-instruct3.8134.0 est.Yes160.8 est.YesRX 7900 XTX 24GB
Phi-4-mini-reasoning3.8134.0 est.Yes160.8 est.YesRX 7900 XTX 24GB
gemma-3-4b-it4.3130.5 est.Yes156.6 est.YesRX 7900 XTX 24GB
Qwen3-Next-80B-A3B-Instruct81.390.4 est.No156.2 est.NoRX 7900 XTX 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

RX 7900 XT 20GBRX 7900 XTX 24GB
Catalog models that fit32 of 6133 of 61
Largest exclusive fitgemma-3-27b-it (27.4B)

RX 7900 XT 20GB details → · RX 7900 XTX 24GB details →