← AI Hashrate 中文

A100 80GB SXM4 vs Ryzen AI Max+ 395 128GB for Local LLMs

The A100 80GB SXM4 has about 848% more memory bandwidth (2,039 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 848% faster on the A100 80GB SXM4. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 50 of 69 models (96 vs 80 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the A100 80GB SXM4: DeepSeek-V4-Flash (158.1B). MSRP is $15,000 for the A100 80GB SXM4 vs $2,000 for the Ryzen AI Max+ 395 128GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: A100 80GB SXM4 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (62 shared models), the A100 80GB SXM4 posts the higher tok/s in 62 rows vs 0. Methodology.

Spec comparison

A100 80GB SXM4Ryzen AI Max+ 395 128GB
VendorNVIDIAAMD
VRAM80 GB96 GB
Memory typeHBM2eLPDDR5X
Memory bandwidth2,039 GB/s215 GB/s
TDP400 W120 W
MSRP (list)$15,000$2,000
BuySearch 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 62 shared models

ModelParams (B)A100 80GB SXM4 tok/sA100 80GB SXM4 fitsRyzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsWinner
MiniCPM5-1B1.081201.4 est.Yes126.7 est.YesA100 80GB SXM4
Qwen3.5-2B2.0648.8 est.Yes68.4 est.YesA100 80GB SXM4
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.3564.2 est.Yes59.5 est.YesA100 80GB SXM4
Qwen3.6-35B-A3B36.0432.5 est.Yes45.6 est.YesA100 80GB SXM4
Qwen3.5-35B-A3B34.7432.5 est.Yes45.6 est.YesA100 80GB SXM4
GLM-4.7-Flash31.2432.5 est.Yes45.6 est.YesA100 80GB SXM4
Qwen3-30B-A3B-Instruct-250730.5432.5 est.Yes45.6 est.YesA100 80GB SXM4
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.0432.5 est.Yes45.6 est.YesA100 80GB SXM4
Qwen3-Coder-Next79.7432.5 est.Yes45.6 est.YesA100 80GB SXM4
Ornith-1.0-35B35.0432.5 est.Yes45.6 est.YesA100 80GB SXM4
Qwen3-Next-80B-A3B-Instruct81.3432.5 est.Yes45.6 est.YesA100 80GB SXM4
qwen35b-a3b-fable-sft-abliterated34.7432.5 est.Yes45.6 est.YesA100 80GB SXM4
Llama-3.2-3B-Instruct3.2405.5 est.Yes42.8 est.YesA100 80GB SXM4
gpt-oss-20b21.5360.4 est.Yes38.0 est.YesA100 80GB SXM4
gemma-4-26B-A4B-it25.2341.5 est.Yes36.0 est.YesA100 80GB SXM4

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

A100 80GB SXM4Ryzen AI Max+ 395 128GB
Catalog models that fit50 of 6951 of 69
Largest exclusive fitDeepSeek-V4-Flash (158.1B)

A100 80GB SXM4 details → · Ryzen AI Max+ 395 128GB details →