← AI Hashrate 中文

Ryzen AI Max 390 64GB vs RTX 4080 Super 16GB for Local LLMs

The RTX 4080 Super 16GB has about 242% more memory bandwidth (736 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 242% faster on the RTX 4080 Super 16GB. The Ryzen AI Max 390 64GB fits more of the catalog at Q4/8K — 41 vs 24 of 69 models (48 vs 16 GB VRAM). Largest model that fits the Ryzen AI Max 390 64GB but not the RTX 4080 Super 16GB: Qwen3-Next-80B-A3B-Instruct (81.3B). MSRP is $1,300 for the Ryzen AI Max 390 64GB vs $999 for the RTX 4080 Super 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 4080 Super 16GB posts the higher tok/s in 41 rows vs 3. Methodology.

Spec comparison

Ryzen AI Max 390 64GBRTX 4080 Super 16GB
VendorAMDNVIDIA
VRAM48 GB16 GB
Memory typeLPDDR5XGDDR6X
Memory bandwidth215 GB/s736 GB/s
TDP120 W320 W
MSRP (list)$1,300$999
BuySearch Amazon (affiliate)ASUS ProArt GeForce RTX 4080 Super 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 44 shared models

ModelParams (B)Ryzen AI Max 390 64GB tok/sRyzen AI Max 390 64GB fitsRTX 4080 Super 16GB tok/sRTX 4080 Super 16GB fitsWinner
MiniCPM5-1B1.08126.7 est.Yes433.7 est.YesRTX 4080 Super 16GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.045.6 est.Yes370.4 est.NoRTX 4080 Super 16GB
Qwen3-30B-A3B-Instruct-250730.545.6 est.Yes337.0 est.NoRTX 4080 Super 16GB
GLM-4.7-Flash31.245.6 est.Yes323.5 est.NoRTX 4080 Super 16GB
Qwen3.5-35B-A3B34.745.6 est.Yes280.1 est.NoRTX 4080 Super 16GB
qwen35b-a3b-fable-sft-abliterated34.745.6 est.Yes265.9 est.NoRTX 4080 Super 16GB
Ornith-1.0-35B35.045.6 est.Yes261.9 est.NoRTX 4080 Super 16GB
Qwen3.6-35B-A3B36.045.6 est.Yes261.1 est.NoRTX 4080 Super 16GB
Qwen3.5-2B2.068.4 est.Yes234.2 est.YesRTX 4080 Super 16GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.359.5 est.Yes203.6 est.YesRTX 4080 Super 16GB
gpt-oss-20b21.538.0 est.Yes186.5 measuredYesRTX 4080 Super 16GB
Llama-3.2-3B-Instruct3.242.8 est.Yes146.4 est.YesRTX 4080 Super 16GB
gemma-4-26B-A4B-it25.236.0 est.Yes123.3 est.YesRTX 4080 Super 16GB
Qwen3-4B-Instruct-25074.034.2 est.Yes117.1 est.YesRTX 4080 Super 16GB
NVIDIA-Nemotron-3-Nano-4B-BF164.034.2 est.Yes117.1 est.YesRTX 4080 Super 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 390 64GBRTX 4080 Super 16GB
Catalog models that fit41 of 6924 of 69
Largest exclusive fitQwen3-Next-80B-A3B-Instruct (81.3B)—

Ryzen AI Max 390 64GB details → · RTX 4080 Super 16GB details →