What AI models can the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (96 GB) run?

Unified memory: 96.0 GB
Usable for models: 72.0 GB
Memory bandwidth: 90 GB/s
FP16 compute: 25.4 TFLOPS
Released: 2026

527 / 621 LLMs run Best: Kolibri 1 (78B-A3.5B) 61 / 61 Image models run Best: Krea 2 Turbo 43 / 43 Video models run Best: LTX-2.5 (22B, video + audio) 70 / 70 Decision models run Best: Jina Reranker v3.5

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 96.0 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 9 HX 470 (DDR5 SO-DIMM)

Apps that run models well on the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (96 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 9 HX 470 (DDR5 SO-DIMM) (96 GB)

Quality	Model	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	Kolibri 1 (78B-A3.5B)Aleph Alpha	`Q4_K_M`	54.2 GB	25.1 tok/s	Runs well
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Coder Next (80B-A3B)Alibaba	`Q4_K_M`	55.2 GB	28.5 tok/s	Runs well
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3-Next 80B-A3B ThinkingAlibaba	`Q4_K_M`	56.2 GB	28.5 tok/s	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Next 80B-A3B InstructAlibaba	`Q4_K_M`	56.2 GB	28.5 tok/s	Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Flint (40B-A2.5B)Recursive	`Q4_K_M`	30.9 GB	33.6 tok/s	Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt 74B-A9BNVIDIA	`Q4_K_M`	52.1 GB	10.2 tok/s	Runs well
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	`Q4_K_M`	28.5 GB	28.5 tok/s	Runs well
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	`Q4_K_M`	28.5 GB	28.5 tok/s	Runs well
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-V 4.7 35B-A3BOpenBMB	`Q4_K_M`	28.0 GB	28.5 tok/s	Runs well
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Nex N2 Mini (35B-A3B)Nex-AGI	`Q4_K_M`	27.9 GB	28.5 tok/s	Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Sage-A1.5 35B-A3BInternScience	`Q4_K_M`	28.5 GB	28.5 tok/s	Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	KAT-Coder V2.5 Dev (35B-A3B)Kuaishou	`Q4_K_M`	27.7 GB	28.5 tok/s	Runs well

Best Image models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (96 GB)

Quality	Model	Quant	Memory	Speed	Runs
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	16 s	Runs well
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`FP16`	37.1 GB	6.5 s	Runs great
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	1.5 min	Slow
85Excellent quality (A+) · 85 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.	ERNIE-Image TurboBaidu	`FP16`	26.4 GB	12 s	Runs great
84Great quality (A) · 84 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.	Z-Image TurboAlibaba (Tongyi)	`FP16`	22.7 GB	9.1 s	Runs great
93Excellent quality (A+) · 93 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.	Qwen-Image 2.1Alibaba	`FP16`	57.0 GB	3.6 min	Very slow

Best Video models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (96 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 90/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.5 (22B, video + audio)Lightricks	`FP8`	48.3 GB	5.0 min	Runs well
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.3Lightricks	`FP8`	44.3 GB	21.8 min	Slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 I2V A14BAlibaba	`FP16`	58.0 GB	1.6 h	Very slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 T2V A14BAlibaba	`FP16`	58.0 GB	1.6 h	Very slow
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax H3 (33B, video + audio)MiniMax	`Q8 GGUF`	68.2 GB	72.4 min	Very slowtight fit

Best Decision models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (96 GB)

Quality	Model	Quant	Memory	Speed	Runs
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`	7.8 GB	51 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`	7.8 GB	51 ms	Runs great
82Great quality (A) · 82 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.	mxbai-rerank-large v2Mixedbread	`Q8_0`	8.1 GB	86 ms	Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	d1 3BLiquid AI	`Q6_K`	9.0 GB	102 ms	Runs great
80Great quality (A) · 80 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.	FRIDA-DecisionsSber AI	`F16`	2.4 GB	21 ms	Runs great
80Great quality (A) · 80 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.	GLiNER2.5 DecideFastino	`F16`	1.7 GB	14 ms	Runs great
80Great quality (A) · 80 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.	LemonDecider 4BAnt Group (inclusionAI)	`F16`	10.8 GB	96 ms	Runs great
80Great quality (A) · 80 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.	Qwen3 Reranker 0.6BAlibaba	`F16`	7.8 GB	51 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.