← AI Hashrate 中文

Ryzen AI Max+ 395 128GB vs RX 7900 XTX 24GB for Local LLMs

The RX 7900 XTX 24GB has about 347% more memory bandwidth (960 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 347% faster on the RX 7900 XTX 24GB. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 35 of 69 models (96 vs 24 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the RX 7900 XTX 24GB: DeepSeek-V4-Flash (158.1B). MSRP is $2,000 for the Ryzen AI Max+ 395 128GB 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 (51 shared models), the RX 7900 XTX 24GB posts the higher tok/s in 50 rows vs 1. Methodology.

Spec comparison

Ryzen AI Max+ 395 128GBRX 7900 XTX 24GB
VendorAMDAMD
VRAM96 GB24 GB
Memory typeLPDDR5XGDDR6
Memory bandwidth215 GB/s960 GB/s
TDP120 W355 W
MSRP (list)$2,000$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 51 shared models

ModelParams (B)Ryzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsRX 7900 XTX 24GB tok/sRX 7900 XTX 24GB fitsWinner
MiniCPM5-1B1.08126.7 est.Yes565.7 est.YesRX 7900 XTX 24GB
Qwen3.5-2B2.068.4 est.Yes305.5 est.YesRX 7900 XTX 24GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.359.5 est.Yes265.6 est.YesRX 7900 XTX 24GB
Qwen3.6-35B-A3B36.045.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
Qwen3.5-35B-A3B34.745.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
GLM-4.7-Flash31.245.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
Qwen3-30B-A3B-Instruct-250730.545.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.045.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
Ornith-1.0-35B35.045.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
qwen35b-a3b-fable-sft-abliterated34.745.6 est.Yes203.6 est.YesRX 7900 XTX 24GB
Llama-3.2-3B-Instruct3.242.8 est.Yes190.9 est.YesRX 7900 XTX 24GB
gpt-oss-20b21.538.0 est.Yes169.7 est.YesRX 7900 XTX 24GB
Qwen3-Coder-Next79.745.6 est.Yes165.8 est.NoRX 7900 XTX 24GB
gemma-4-26B-A4B-it25.236.0 est.Yes160.8 est.YesRX 7900 XTX 24GB
Qwen3-Next-80B-A3B-Instruct81.345.6 est.Yes159.5 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

Ryzen AI Max+ 395 128GBRX 7900 XTX 24GB
Catalog models that fit51 of 6935 of 69
Largest exclusive fitDeepSeek-V4-Flash (158.1B)

Ryzen AI Max+ 395 128GB details → · RX 7900 XTX 24GB details →