What AI models can the AMD Ryzen AI Max 390 (128 GB) run?

Unified memory: 128 GB
Usable for models: 96.0 GB
Memory bandwidth: 256 GB/s
FP16 compute: 45.9 TFLOPS
Released: 2025

547 / 621 LLMs run Best: Kolibri 1 (78B-A3.5B) 61 / 61 Image models run Best: MiniMax H3 Image 43 / 43 Video models run Best: LTX-2.5 (22B, video + audio) 70 / 70 Decision models run Best: Qwen3 Reranker 4B

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 128 GB.

More about this hardware

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	AMD Ryzen AI Max 390

Apps that run models well on the AMD Ryzen AI Max 390 (128 GB)

Windows

Linux

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

Best LLMs for the AMD Ryzen AI Max 390 (128 GB)

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Kolibri 1 (78B-A3.5B)Aleph Alpha	`Q6_K`	72.5 GB	45.4 tok/s	Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Coder Next (80B-A3B)Alibaba	`Q6_K`	73.8 GB	51.1 tok/s	Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3-Next 80B-A3B ThinkingAlibaba	`Q6_K`	75.2 GB	51.1 tok/s	Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	`Q8_0`	46.6 GB	39.1 tok/s	Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	`Q8_0`	46.6 GB	39.1 tok/s	Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-V 4.7 35B-A3BOpenBMB	`Q8_0`	45.8 GB	39.1 tok/s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	gpt-oss 120BOpenAI	`MXFP4`	75.2 GB	47.7 tok/s	Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Flint (40B-A2.5B)Recursive	`Q8_0`	50.7 GB	45.6 tok/s	Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Next 80B-A3B InstructAlibaba	`Q6_K`	75.2 GB	51.1 tok/s	Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Nex N2 Mini (35B-A3B)Nex-AGI	`Q8_0`	45.7 GB	39.1 tok/s	Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Sage-A1.5 35B-A3BInternScience	`Q8_0`	46.6 GB	39.1 tok/s	Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	KAT-Coder V2.5 Dev (35B-A3B)Kuaishou	`Q8_0`	45.2 GB	39.1 tok/s	Runs great

Best Image models for the AMD Ryzen AI Max 390 (128 GB)

Quality	Model	Quant	Memory	Speed	Runs
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax H3 ImageMiniMax	`FP8`	72.0 GB	21 s	Runs well
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	Krea 2 TurboKrea	`FP16`	37.4 GB	10 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`FP16`	37.1 GB	4.2 s	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Ming-Image 0.1 DesignAnt Group (inclusionAI)	`FP16`	63.9 GB	38 s	Runs well
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Ideogram 4Ideogram	`FP16`	57.3 GB	58 s	Slow
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Cosmos3-Super Text2Image (64B)NVIDIA	`FP8`	69.1 GB	84 s	Slow

Best Video models for the AMD Ryzen AI Max 390 (128 GB)

Quality	Model	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.5 (22B, video + audio)Lightricks	`FP8`	48.3 GB	3.2 min	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.3Lightricks	`FP16`	75.4 GB	15.5 min	Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax H3 (33B, video + audio)MiniMax	`FP8`	66.8 GB	36.4 min	Slow
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2 (19B, video + audio)Lightricks	`FP16`	75.4 GB	15.5 min	Slow
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 13B 0.9.8 (distilled)Lightricks	`FP16`	47.9 GB	2.3 min	Runs great

Best Decision models for the AMD Ryzen AI Max 390 (128 GB)

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	`Q8_0`	12.8 GB	106 ms	Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	zerank-2ZeroEntropy	`Q6_K`	11.9 GB	98 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`F16`	9.7 GB	24 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	`Q8_0`	12.6 GB	101 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Intern-Decision 4BShanghai AI Lab	`Q8_0`	13.2 GB	78 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`F16`	9.7 GB	24 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	d1 3BLiquid AI	`F16`	14.6 GB	81 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-large v2Mixedbread	`F16`	11.4 GB	56 ms	Runs great

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.