← AI Hashrate 中文

Ryzen AI Max+ 395 128GB vs RX 7900 XT 20GB for Local LLMs

The RX 7900 XT 20GB has about 272% more memory bandwidth (800 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 272% faster on the RX 7900 XT 20GB. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 30 of 69 models (96 vs 20 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the RX 7900 XT 20GB: DeepSeek-V4-Flash (158.1B). MSRP is $2,000 for the Ryzen AI Max+ 395 128GB 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 (50 shared models), the RX 7900 XT 20GB posts the higher tok/s in 46 rows vs 4. Methodology.

Spec comparison

Ryzen AI Max+ 395 128GBRX 7900 XT 20GB
VendorAMDAMD
VRAM96 GB20 GB
Memory typeLPDDR5XGDDR6
Memory bandwidth215 GB/s800 GB/s
TDP120 W315 W
MSRP (list)$2,000$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 50 shared models

ModelParams (B)Ryzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsRX 7900 XT 20GB tok/sRX 7900 XT 20GB fitsWinner
Qwen3.5-35B-A3B34.745.6 est.Yes476.0 est.NoRX 7900 XT 20GB
MiniCPM5-1B1.08126.7 est.Yes471.4 est.YesRX 7900 XT 20GB
qwen35b-a3b-fable-sft-abliterated34.745.6 est.Yes451.9 est.NoRX 7900 XT 20GB
Ornith-1.0-35B35.045.6 est.Yes445.0 est.NoRX 7900 XT 20GB
Qwen3.6-35B-A3B36.045.6 est.Yes443.7 est.NoRX 7900 XT 20GB
Qwen3.5-2B2.068.4 est.Yes254.5 est.YesRX 7900 XT 20GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.359.5 est.Yes221.3 est.YesRX 7900 XT 20GB
GLM-4.7-Flash31.245.6 est.Yes169.7 est.YesRX 7900 XT 20GB
Qwen3-30B-A3B-Instruct-250730.545.6 est.Yes169.7 est.YesRX 7900 XT 20GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.045.6 est.Yes169.7 est.YesRX 7900 XT 20GB
gpt-oss-20b21.538.0 est.Yes141.4 est.YesRX 7900 XT 20GB
gemma-4-26B-A4B-it25.236.0 est.Yes134.0 est.YesRX 7900 XT 20GB
Llama-3.2-3B-Instruct3.242.8 est.Yes131.2 measuredYesRX 7900 XT 20GB
Qwen3-4B-Instruct-25074.034.2 est.Yes127.3 est.YesRX 7900 XT 20GB
NVIDIA-Nemotron-3-Nano-4B-BF164.034.2 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

Ryzen AI Max+ 395 128GBRX 7900 XT 20GB
Catalog models that fit51 of 6930 of 69
Largest exclusive fitDeepSeek-V4-Flash (158.1B)

Ryzen AI Max+ 395 128GB details → · RX 7900 XT 20GB details →