← AI Hashrate 中文

Ryzen AI Max+ 395 128GB vs V100 32GB SXM2 for Local LLMs

The V100 32GB SXM2 has about 319% more memory bandwidth (900 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 319% faster on the V100 32GB SXM2. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 56 vs 43 of 73 models (96 vs 32 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the V100 32GB SXM2: DeepSeek-V4-Flash (158.1B). MSRP is $2,000 for the Ryzen AI Max+ 395 128GB vs $10,000 for the V100 32GB SXM2. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: V100 32GB SXM2 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (57 shared models), the V100 32GB SXM2 posts the higher tok/s in 55 rows vs 2. Methodology.

Spec comparison

Ryzen AI Max+ 395 128GBV100 32GB SXM2
VendorAMDNVIDIA
VRAM96 GB32 GB
Memory typeLPDDR5XHBM2
Memory bandwidth215 GB/s900 GB/s
TDP120 W300 W
MSRP (list)$2,000$10,000
BuySearch Amazon

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 57 shared models

ModelParams (B)Ryzen AI Max+ 395 128GB tok/sRyzen AI Max+ 395 128GB fitsV100 32GB SXM2 tok/sV100 32GB SXM2 fitsWinner
MiniCPM5-1B1.08204.4 est.Yes895.6 est.YesV100 32GB SXM2
Qwen3.5-2B2.0110.4 est.Yes483.6 est.YesV100 32GB SXM2
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.396.0 est.Yes420.5 est.YesV100 32GB SXM2
Qwen3.6-35B-A3B36.073.6 est.Yes322.4 est.YesV100 32GB SXM2
Qwen3.5-35B-A3B34.773.6 est.Yes322.4 est.YesV100 32GB SXM2
GLM-4.7-Flash31.273.6 est.Yes322.4 est.YesV100 32GB SXM2
Qwen3-30B-A3B-Instruct-250730.573.6 est.Yes322.4 est.YesV100 32GB SXM2
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.073.6 est.Yes322.4 est.YesV100 32GB SXM2
Ornith-1.0-35B35.073.6 est.Yes322.4 est.YesV100 32GB SXM2
qwen35b-a3b-fable-sft-abliterated34.773.6 est.Yes322.4 est.YesV100 32GB SXM2
Llama-3.2-3B-Instruct3.269.0 est.Yes302.3 est.YesV100 32GB SXM2
gpt-oss-20b21.561.3 est.Yes268.7 est.YesV100 32GB SXM2
Qwen3-Coder-Next79.773.6 est.Yes268.3 est.NoV100 32GB SXM2
Qwen3-Next-80B-A3B-Instruct81.373.6 est.Yes258.2 est.NoV100 32GB SXM2
gemma-4-26B-A4B-it25.258.1 est.Yes254.5 est.YesV100 32GB SXM2

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 128GBV100 32GB SXM2
Catalog models that fit56 of 7343 of 73
Largest exclusive fitDeepSeek-V4-Flash (158.1B)

Ryzen AI Max+ 395 128GB details → · V100 32GB SXM2 details →