← AI Hashrate 中文

Ryzen AI Max+ 395 128GB vs RTX 5080 16GB for Local LLMs

The RTX 5080 16GB 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 RTX 5080 16GB. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 24 of 69 models (96 vs 16 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the RTX 5080 16GB: DeepSeek-V4-Flash (158.1B). MSRP is $2,000 for the Ryzen AI Max+ 395 128GB vs $999 for the RTX 5080 16GB. 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 RTX 5080 16GB posts the higher tok/s in 44 rows vs 0. Methodology.

Spec comparison

Ryzen AI Max+ 395 128GBRTX 5080 16GB
VendorAMDNVIDIA
VRAM96 GB16 GB
Memory typeLPDDR5XGDDR7
Memory bandwidth215 GB/s960 GB/s
TDP120 W360 W
MSRP (list)$2,000$999
BuySearch Amazon (affiliate)NVIDIA GeForce RTX 5080 Founders Edition (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 44 shared models

ModelParams (B)Ryzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsRTX 5080 16GB tok/sRTX 5080 16GB fitsWinner
MiniCPM5-1B1.08126.7 est.Yes565.7 est.YesRTX 5080 16GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.045.6 est.Yes483.2 est.NoRTX 5080 16GB
Qwen3-30B-A3B-Instruct-250730.545.6 est.Yes439.5 est.NoRTX 5080 16GB
GLM-4.7-Flash31.245.6 est.Yes421.9 est.NoRTX 5080 16GB
Qwen3.5-35B-A3B34.745.6 est.Yes365.3 est.NoRTX 5080 16GB
qwen35b-a3b-fable-sft-abliterated34.745.6 est.Yes346.9 est.NoRTX 5080 16GB
Ornith-1.0-35B35.045.6 est.Yes341.6 est.NoRTX 5080 16GB
Qwen3.6-35B-A3B36.045.6 est.Yes340.6 est.NoRTX 5080 16GB
Qwen3.5-2B2.068.4 est.Yes305.5 est.YesRTX 5080 16GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.359.5 est.Yes265.6 est.YesRTX 5080 16GB
gpt-oss-20b21.538.0 est.Yes204.9 measuredYesRTX 5080 16GB
Llama-3.2-3B-Instruct3.242.8 est.Yes190.9 est.YesRTX 5080 16GB
Mistral-7B-Instruct-v0.37.219.0 est.Yes163.6 measuredYesRTX 5080 16GB
gemma-4-26B-A4B-it25.236.0 est.Yes160.8 est.YesRTX 5080 16GB
Qwen3-4B-Instruct-25074.034.2 est.Yes152.7 est.YesRTX 5080 16GB

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 128GBRTX 5080 16GB
Catalog models that fit51 of 6924 of 69
Largest exclusive fitDeepSeek-V4-Flash (158.1B)—

Ryzen AI Max+ 395 128GB details → · RTX 5080 16GB details →