GEEKOM A9 Max 2026 Edition

Hardware · AMD

What AI models can the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB) run?

Unified memory
32.0 GB
Usable for models
24.0 GB
Memory bandwidth
90 GB/s
FP16 compute
25.4 TFLOPS
Released
2026
463 / 621 LLMs run Best: Gemma 4 26B-A4B 58 / 61 Image models run Best: Krea 2 Turbo 31 / 43 Video models run Best: LTX-Video 2B 67 / 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 32.0 GB.

More about this hardware

MakerAMD
TypeUnified-memory system on a chip
GPU share of memory75% (what the GPU can typically be given for a model)
ChipAMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM)

Apps that run models well on the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Windows

  1. LemonadeBuilt for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaOne command with Ollama’s own build of this model.
  4. llama.cppUsually the first to support new model architectures.

Linux

  1. LemonadeBuilt for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaOne command with Ollama’s own build of this model.
  4. llama.cppUsually the first to support new model architectures.

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

1 product with the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Best LLMs for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Quality Model Quant Memory Speed Runs
87Excellent quality (A+) · 87 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. Gemma 4 26B-A4BGoogle Q4_K_M 18.7 GB 23.0 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 90/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q4_K_M 23.8 GB 28.5 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba Q3_K_M 20.3 GB 36.0 tok/s Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB Q3_K_M 19.9 GB 36.0 tok/s Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba Q3_K_M 20.3 GB 36.0 tok/s Runs great
83Great quality (A) · 83 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. GLM-4.7 Flash (30B-A3B)Zhipu AI Q4_K_M 22.0 GB 28.5 tok/s Runs welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q3_K_M 19.9 GB 36.0 tok/s Runs great
82Great quality (A) · 82 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. Qwen AgentWorld 35B-A3BAlibaba Q4_K_M 23.8 GB 28.5 tok/s Runs welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q3_K_M 20.3 GB 36.0 tok/s Runs great
83Great quality (A) · 83 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. Raon-1 mini Preview (30B-A4B)KRAFTON Q4_K_M 20.1 GB 20.5 tok/s Runs well
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce Q3_K_M 20.3 GB 36.0 tok/s Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B)Recursive Q3_K_M 22.3 GB 42.3 tok/s Runs welltight fit

Best Image models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 20.2 GB 14 s Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP8 19.9 GB 5.9 s Runs great
83Great quality (A) · 83 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. ERNIE-Image TurboBaidu FP8 14.5 GB 10 s Runs great
78Great quality (A) · 78 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. FLUX.2 [klein] 4BBlack Forest Labs FP16 18.1 GB 3.6 s Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) Q8 GGUF 13.0 GB 10 s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 19 s Runs well

Best Video models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 GB)

Quality Model Quant Memory Speed Runs
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP16 17.5 GB 1.5 min Runs great
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 20.3 GB 41.2 min Very slowencoder unloaded after use
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks FP8 19.7 GB 6.4 min Runs wellCPU offload
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 15.7 GB 30.3 min Slowencoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. FramePack I2V (HunyuanVideo 13B)lllyasviel FP8 19.6 GB 22.9 min Slowencoder unloaded after use

Best Decision models for the AMD Ryzen AI 9 HX 470 (DDR5 SO-DIMM) (32 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 4.0 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 4.0 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 4.2 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 5.1 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 4.0 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.

Was this page helpful?