What AI models can the AMD Ryzen AI Max 390 (32 GB) run?

Unified memory: 32.0 GB
Usable for models: 24.0 GB
Memory bandwidth: 256 GB/s
FP16 compute: 45.9 TFLOPS
Released: 2025

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 32.0 GB.

Specifications

Maker	AMD
Type	Unified-memory system on a chip
GPU share of memory	75% (what the GPU can typically be given for a model)
Chip	Apple AMD Ryzen AI Max 390
Unified memory	32.0 GB
Usable for AI models	24.0 GB
Memory bandwidth	256 GB/s
FP16 compute	45.9 TFLOPS
Interface	UNIFIED
Released	2025

1 product with the AMD Ryzen AI Max 390 (32 GB)

ROG Flow Z13 (2025) GZ302ASUS · Laptop · 32, 64 or 128 GB · from $2,100Maker’s page (opens in a new tab)

Best LLMs for the AMD Ryzen AI Max 390 (32 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 15.0/15	Gemma 4 26B-A4BGoogle	`Q4_K_M`	18.7 GB	35.6 tok/s	Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	GLM-4.7 Flash (30B-A3B)Zhipu AI	`Q4_K_M`	22.0 GB	45.1 tok/s	Tight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen AgentWorld 35B-A3BAlibaba	`Q4_K_M`	23.8 GB	45.1 tok/s	Tight fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.6 35B-A3BAlibaba	`Q3_K_M`	20.3 GB	58.3 tok/s	Runs well
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.5 35B-A3BAlibaba	`Q3_K_M`	20.3 GB	58.3 tok/s	Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.5 35B-A3BDeepReinforce	`Q3_K_M`	20.3 GB	58.3 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Apodex 1.1 Mini (35B-A3B)Apodex	`Q3_K_M`	20.3 GB	58.3 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.0 35B-A3BDeepReinforce	`Q3_K_M`	20.3 GB	58.3 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 15.0/15	Qwen3.8 27BAlibaba	`Q4_K_M`	20.0 GB	9.7 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	North Mini Code 1.0 (30B-A3B)Cohere	`Q4_K_M`	21.4 GB	45.1 tok/s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15	Nemotron Cascade 2 30B-A3BNVIDIA	`Q4_K_M`	21.8 GB	38.7 tok/s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Agents-A1 35B-A3BInternScience	`Q3_K_M`	19.9 GB	58.3 tok/s	Runs well

Best Image models for the AMD Ryzen AI Max 390 (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`FP8`	19.9 GB	3.8 s	Runs well
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs	`FP16`	18.1 GB	2.3 s	Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15	Z-Image TurboAlibaba (Tongyi)	`Q8 GGUF`	13.0 GB	6.7 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.1 [schnell]Black Forest Labs	`FP8`	19.6 GB	4.2 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 9.5/15, Memory use 15.0/15	FLUX.1 Krea [dev]Black Forest Labs	`FP8`	19.6 GB	25 s	Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 9.5/15, Memory use 15.0/15	FLUX.1 [dev]Black Forest Labs	`FP8`	19.6 GB	25 s	Runs well

Best Video models for the AMD Ryzen AI Max 390 (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	LTX-Video 2BLightricks	`FP16`	17.5 GB	58 s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	CogVideoX 2BZhipu AI	`FP16`	17.5 GB	2.3 min	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 6.8/15, Memory use 15.0/15	FramePack I2V (HunyuanVideo 13B)lllyasviel	`FP8`	19.6 GB	14.7 min	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 14.3/15	CogVideoX 5B I2VZhipu AI	`FP8`	14.9 GB	6.3 min	Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 31.8/45, Memory fit 23.0/25, Speed 3.8/15, Memory use 15.0/15	Wan 2.2 S2V 14B (speech to video)Alibaba	`Q4 GGUF`	21.6 GB	46.6 min	Tight fit

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.