← AI Hashrate 中文

Ryzen AI Max+ 395 128GB vs Mac mini M4 32GB for Local LLMs

The Ryzen AI Max+ 395 128GB has about 79% more memory bandwidth (215 vs 120 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 79% faster on the Ryzen AI Max+ 395 128GB. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 39 of 69 models (96 vs 32 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the Mac mini M4 32GB: DeepSeek-V4-Flash (158.1B). MSRP is $2,000 for the Ryzen AI Max+ 395 128GB vs $999 for the Mac mini M4 32GB. 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 (53 shared models), the Ryzen AI Max+ 395 128GB posts the higher tok/s in 52 rows vs 1. Methodology.

Spec comparison

Ryzen AI Max+ 395 128GBMac mini M4 32GB
VendorAMDApple
VRAM96 GB32 GB
Memory typeLPDDR5XLPDDR5X
Memory bandwidth215 GB/s120 GB/s
TDP120 W155 W
MSRP (list)$2,000$999
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 53 shared models

ModelParams (B)Ryzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsMac mini M4 32GB tok/sMac mini M4 32GB fitsWinner
MiniCPM5-1B1.08126.7 est.Yes70.7 est.YesRyzen AI Max+ 395 128GB
Qwen3.5-2B2.068.4 est.Yes38.2 est.YesRyzen AI Max+ 395 128GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.359.5 est.Yes33.2 est.YesRyzen AI Max+ 395 128GB
Qwen3.6-35B-A3B36.045.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Qwen3.5-35B-A3B34.745.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
GLM-4.7-Flash31.245.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Qwen3-30B-A3B-Instruct-250730.545.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.045.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Qwen3-Coder-Next79.745.6 est.Yes36.9 est.NoRyzen AI Max+ 395 128GB
Ornith-1.0-35B35.045.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Qwen3-Next-80B-A3B-Instruct81.345.6 est.Yes35.5 est.NoRyzen AI Max+ 395 128GB
qwen35b-a3b-fable-sft-abliterated34.745.6 est.Yes25.5 est.YesRyzen AI Max+ 395 128GB
Llama-3.2-3B-Instruct3.242.8 est.Yes41.3 measuredYesRyzen AI Max+ 395 128GB
gpt-oss-20b21.538.0 est.Yes21.2 est.YesRyzen AI Max+ 395 128GB
gemma-4-26B-A4B-it25.236.0 est.Yes20.1 est.YesRyzen AI Max+ 395 128GB

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 128GBMac mini M4 32GB
Catalog models that fit51 of 6939 of 69
Largest exclusive fitDeepSeek-V4-Flash (158.1B)

Ryzen AI Max+ 395 128GB details → · Mac mini M4 32GB details →