Ryzen AI Max 390 64GB vs RTX 3080 10GB for Local LLMs

The RTX 3080 10GB has about 253% more memory bandwidth (760 vs 215 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 253% faster on the RTX 3080 10GB. The Ryzen AI Max 390 64GB fits more of the catalog at Q4/8K — 41 vs 17 of 69 models (48 vs 10 GB VRAM). Largest model that fits the Ryzen AI Max 390 64GB but not the RTX 3080 10GB: Qwen3-Next-80B-A3B-Instruct (81.3B). MSRP is $1,300 for the Ryzen AI Max 390 64GB vs $699 for the RTX 3080 10GB. 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 (39 shared models), the RTX 3080 10GB posts the higher tok/s in 39 rows vs 0. Methodology.

Spec comparison

	Ryzen AI Max 390 64GB	RTX 3080 10GB
Vendor	AMD	NVIDIA
VRAM	48 GB	10 GB
Memory type	LPDDR5X	GDDR6X
Memory bandwidth	215 GB/s	760 GB/s
TDP	120 W	320 W
MSRP (list)	$1,300	$699
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 39 shared models

Model	Params (B)	Ryzen AI Max 390 64GB tok/s	Ryzen AI Max 390 64GB fits	RTX 3080 10GB tok/s	RTX 3080 10GB fits	Winner
MiniCPM5-1B	1.08	126.7 est.	Yes	447.8 est.	Yes	RTX 3080 10GB
Qwen3.5-2B	2.0	68.4 est.	Yes	241.8 est.	Yes	RTX 3080 10GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	59.5 est.	Yes	210.3 est.	Yes	RTX 3080 10GB
gpt-oss-20b	21.5	38.0 est.	Yes	208.0 est.	No	RTX 3080 10GB
Llama-3.2-3B-Instruct	3.2	42.8 est.	Yes	151.1 est.	Yes	RTX 3080 10GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	45.6 est.	Yes	149.1 est.	No	RTX 3080 10GB
gemma-4-26B-A4B-it	25.2	36.0 est.	Yes	148.3 est.	No	RTX 3080 10GB
Qwen3-30B-A3B-Instruct-2507	30.5	45.6 est.	Yes	135.7 est.	No	RTX 3080 10GB
GLM-4.7-Flash	31.2	45.6 est.	Yes	130.2 est.	No	RTX 3080 10GB
Qwen3-4B-Instruct-2507	4.0	34.2 est.	Yes	120.9 est.	Yes	RTX 3080 10GB
NVIDIA-Nemotron-3-Nano-4B-BF16	4.0	34.2 est.	Yes	120.9 est.	Yes	RTX 3080 10GB
Qwen3-4B-Thinking-2507	4.0	34.2 est.	Yes	120.9 est.	Yes	RTX 3080 10GB
Qwen3.5-35B-A3B	34.7	45.6 est.	Yes	112.8 est.	No	RTX 3080 10GB
qwen35b-a3b-fable-sft-abliterated	34.7	45.6 est.	Yes	107.1 est.	No	RTX 3080 10GB
Ornith-1.0-35B	35.0	45.6 est.	Yes	105.4 est.	No	RTX 3080 10GB

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	RTX 3080 10GB
Catalog models that fit	41 of 69	17 of 69
Largest exclusive fit	Qwen3-Next-80B-A3B-Instruct (81.3B)	—

Ryzen AI Max 390 64GB details → · RTX 3080 10GB details →