Ryzen AI Max 390 64GB vs Ryzen AI Max+ 395 128GB for Local LLMs

Both list the same memory bandwidth (215 GB/s), so per-token decode speed should be similar whenever a model fits both. The Ryzen AI Max+ 395 128GB fits more of the catalog at Q4/8K — 51 vs 41 of 69 models (96 vs 48 GB VRAM). Largest model that fits the Ryzen AI Max+ 395 128GB but not the Ryzen AI Max 390 64GB: DeepSeek-V4-Flash (158.1B). MSRP is $1,300 for the Ryzen AI Max 390 64GB 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. In the Q4/8K head-to-head below (57 shared models), the Ryzen AI Max 390 64GB posts the higher tok/s in 9 rows vs 7. Methodology.

Spec comparison

	Ryzen AI Max 390 64GB	Ryzen AI Max+ 395 128GB
Vendor	AMD	AMD
VRAM	48 GB	96 GB
Memory type	LPDDR5X	LPDDR5X
Memory bandwidth	215 GB/s	215 GB/s
TDP	120 W	120 W
MSRP (list)	$1,300	$2,000
Buy	Search 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 57 shared models

Model	Params (B)	Ryzen AI Max 390 64GB tok/s	Ryzen AI Max 390 64GB fits	Ryzen AI Max+ 395 128GB tok/s	Ryzen AI Max+ 395 128GB fits	Winner
MiniCPM5-1B	1.08	126.7 est.	Yes	126.7 est.	Yes	Tie
Qwen3.5-2B	2.0	68.4 est.	Yes	68.4 est.	Yes	Tie
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	59.5 est.	Yes	59.5 est.	Yes	Tie
Qwen3.6-35B-A3B	36.0	45.6 est.	Yes	45.6 est.	Yes	Tie
Qwen3.5-35B-A3B	34.7	45.6 est.	Yes	45.6 est.	Yes	Tie
GLM-4.7-Flash	31.2	45.6 est.	Yes	45.6 est.	Yes	Tie
Qwen3-30B-A3B-Instruct-2507	30.5	45.6 est.	Yes	45.6 est.	Yes	Tie
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	45.6 est.	Yes	45.6 est.	Yes	Tie
Qwen3-Coder-Next	79.7	45.6 est.	Yes	45.6 est.	Yes	Tie
Ornith-1.0-35B	35.0	45.6 est.	Yes	45.6 est.	Yes	Tie
Qwen3-Next-80B-A3B-Instruct	81.3	45.6 est.	Yes	45.6 est.	Yes	Tie
qwen35b-a3b-fable-sft-abliterated	34.7	45.6 est.	Yes	45.6 est.	Yes	Tie
Llama-3.2-3B-Instruct	3.2	42.8 est.	Yes	42.8 est.	Yes	Tie
gpt-oss-20b	21.5	38.0 est.	Yes	38.0 est.	Yes	Tie
gpt-oss-120b	120.4	37.9 est.	No	26.8 est.	Yes	Ryzen AI Max 390 64GB

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 64GB	Ryzen AI Max+ 395 128GB
Catalog models that fit	41 of 69	51 of 69
Largest exclusive fit	—	DeepSeek-V4-Flash (158.1B)

Ryzen AI Max 390 64GB details → · Ryzen AI Max+ 395 128GB details →