Ryzen AI Max 390 64GB vs RX 7900 GRE 16GB for Local LLMs

The RX 7900 GRE 16GB has about 168% more memory bandwidth (576 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 168% faster on the RX 7900 GRE 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 RX 7900 GRE 16GB: Qwen3-Next-80B-A3B-Instruct (81.3B). MSRP is $1,300 for the Ryzen AI Max 390 64GB vs $549 for the RX 7900 GRE 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 RX 7900 GRE 16GB posts the higher tok/s in 39 rows vs 5. Methodology.

Spec comparison

	Ryzen AI Max 390 64GB	RX 7900 GRE 16GB
Vendor	AMD	AMD
VRAM	48 GB	16 GB
Memory type	LPDDR5X	GDDR6
Memory bandwidth	215 GB/s	576 GB/s
TDP	120 W	260 W
MSRP (list)	$1,300	$549
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 44 shared models

Model	Params (B)	Ryzen AI Max 390 64GB tok/s	Ryzen AI Max 390 64GB fits	RX 7900 GRE 16GB tok/s	RX 7900 GRE 16GB fits	Winner
MiniCPM5-1B	1.08	126.7 est.	Yes	339.4 est.	Yes	RX 7900 GRE 16GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	45.6 est.	Yes	289.9 est.	No	RX 7900 GRE 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	45.6 est.	Yes	263.7 est.	No	RX 7900 GRE 16GB
GLM-4.7-Flash	31.2	45.6 est.	Yes	253.1 est.	No	RX 7900 GRE 16GB
Qwen3.5-35B-A3B	34.7	45.6 est.	Yes	219.2 est.	No	RX 7900 GRE 16GB
qwen35b-a3b-fable-sft-abliterated	34.7	45.6 est.	Yes	208.1 est.	No	RX 7900 GRE 16GB
Ornith-1.0-35B	35.0	45.6 est.	Yes	204.9 est.	No	RX 7900 GRE 16GB
Qwen3.6-35B-A3B	36.0	45.6 est.	Yes	204.3 est.	No	RX 7900 GRE 16GB
Qwen3.5-2B	2.0	68.4 est.	Yes	183.3 est.	Yes	RX 7900 GRE 16GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	59.5 est.	Yes	159.4 est.	Yes	RX 7900 GRE 16GB
Llama-3.2-3B-Instruct	3.2	42.8 est.	Yes	114.5 est.	Yes	RX 7900 GRE 16GB
gpt-oss-20b	21.5	38.0 est.	Yes	101.8 est.	Yes	RX 7900 GRE 16GB
gemma-4-26B-A4B-it	25.2	36.0 est.	Yes	96.5 est.	Yes	RX 7900 GRE 16GB
Qwen3-4B-Instruct-2507	4.0	34.2 est.	Yes	91.6 est.	Yes	RX 7900 GRE 16GB
NVIDIA-Nemotron-3-Nano-4B-BF16	4.0	34.2 est.	Yes	91.6 est.	Yes	RX 7900 GRE 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 64GB	RX 7900 GRE 16GB
Catalog models that fit	41 of 69	24 of 69
Largest exclusive fit	Qwen3-Next-80B-A3B-Instruct (81.3B)	—

Ryzen AI Max 390 64GB details → · RX 7900 GRE 16GB details →