ASUS ROG Flow Z13 (2025) GZ302: which AI models can it run?

Estimated from the specifications below. Choose the memory size you have or plan to buy, then read the table for that size.

Specifications

Brand
ASUS
Year
2025
Chip
AMD Ryzen AI Max+ 395
Processor
AMD Ryzen AI Max+ 395 (16 cores)
Graphics
AMD Radeon 8060S (integrated)
Memory type
LPDDR5X-8000 onboard
Memory options
32 GB, 64 GB, 128 GB
Memory bandwidth
256 GB/s

Sources: https://rog.asus.com/us/laptops/rog-flow/rog-flow-z13-2025/spec/, https://www.amd.com/en/products/processors/desktops/ryzen/ryzen-ai-halo/ryzen-ai-max-plus-395.html

Bandwidth is AMD's figure for the Ryzen AI Max+ 395 (on its Ryzen AI Halo page). The spec page lists 32GB, 64GB and 128GB onboard memory.

With 32 GB of memory

About 28 GB of it can hold a model.

ModelFitNeeds (GB)Writing speed (tokens per second)SpeedQualityBasis
Llama 3.2 3B
llama3.2:3b
Fits 5 45 to 83 Fast not measured yet Estimated
Qwen3 4B
qwen3:4b · thinks first
Fits 6 36 to 67 Fast not measured yet Estimated
Gemma 3 4B
gemma3:4b
Fits 6.7 27 to 50 Fast not measured yet Estimated
Mistral 7B v0.3
mistral:7b
Fits 7.8 20 to 38 Fast not measured yet Estimated
Llama 3.1 8B
llama3.1:8b
Fits 8.3 18 to 34 Fast not measured yet Estimated
Qwen3 8B
qwen3:8b · thinks first
Fits 8.9 17 to 32 Fast not measured yet Estimated
Gemma 3 12B
gemma3:12b
Fits 15.9 11 to 21 Fast not measured yet Estimated
DeepSeek-R1 Distill Qwen 14B
deepseek-r1:14b · thinks first
Fits 13.7 10 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Phi-4 14B
phi4:14b
Fits 13.9 9.8 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Qwen3 14B
qwen3:14b · thinks first
Fits 13.4 9.6 to 18 Unclear could be Moderate or Fast not measured yet Estimated
gpt-oss 20B
gpt-oss:20b · thinks first
Fits 16.5 22 to 41 Fast not measured yet Estimated
Gemma 3 27B
gemma3:27b
Tight 27.2 5.3 to 9.8 Moderate not measured yet Estimated
Qwen3 30B (A3B)
qwen3:30b · thinks first
Fits 22.6 26 to 49 Fast 9.3/10 Estimated
Qwen3 32B
qwen3:32b · thinks first
Tight 26.3 4.5 to 8.3 Unclear could be Slow or Moderate not measured yet Estimated
Llama 3.1 70B
llama3.1:70b
Won't fit 51.5 not known n/a not measured yet Estimated
gpt-oss 120B
gpt-oss:120b
Won't fit 70.5 not known n/a not measured yet Estimated

Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.

With 64 GB of memory

About 60 GB of it can hold a model.

ModelFitNeeds (GB)Writing speed (tokens per second)SpeedQualityBasis
Llama 3.2 3B
llama3.2:3b
Fits 5 45 to 83 Fast not measured yet Estimated
Qwen3 4B
qwen3:4b · thinks first
Fits 6 36 to 67 Fast not measured yet Estimated
Gemma 3 4B
gemma3:4b
Fits 6.7 27 to 50 Fast not measured yet Estimated
Mistral 7B v0.3
mistral:7b
Fits 7.8 20 to 38 Fast not measured yet Estimated
Llama 3.1 8B
llama3.1:8b
Fits 8.3 18 to 34 Fast not measured yet Estimated
Qwen3 8B
qwen3:8b · thinks first
Fits 8.9 17 to 32 Fast not measured yet Estimated
Gemma 3 12B
gemma3:12b
Fits 15.9 11 to 21 Fast not measured yet Estimated
DeepSeek-R1 Distill Qwen 14B
deepseek-r1:14b · thinks first
Fits 13.7 10 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Phi-4 14B
phi4:14b
Fits 13.9 9.8 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Qwen3 14B
qwen3:14b · thinks first
Fits 13.4 9.6 to 18 Unclear could be Moderate or Fast not measured yet Estimated
gpt-oss 20B
gpt-oss:20b · thinks first
Fits 16.5 22 to 41 Fast not measured yet Estimated
Gemma 3 27B
gemma3:27b
Fits 27.2 5.3 to 9.8 Moderate not measured yet Estimated
Qwen3 30B (A3B)
qwen3:30b · thinks first
Fits 22.6 26 to 49 Fast 9.3/10 Estimated
Qwen3 32B
qwen3:32b · thinks first
Fits 26.3 4.5 to 8.3 Unclear could be Slow or Moderate not measured yet Estimated
Llama 3.1 70B
llama3.1:70b
Fits 51.5 2.1 to 3.9 Slow not measured yet Estimated
gpt-oss 120B
gpt-oss:120b
Won't fit 70.5 not known n/a not measured yet Estimated

Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.

With 128 GB of memory

About 124 GB of it can hold a model.

ModelFitNeeds (GB)Writing speed (tokens per second)SpeedQualityBasis
Llama 3.2 3B
llama3.2:3b
Fits 5 45 to 83 Fast not measured yet Estimated
Qwen3 4B
qwen3:4b · thinks first
Fits 6 36 to 67 Fast not measured yet Estimated
Gemma 3 4B
gemma3:4b
Fits 6.7 27 to 50 Fast not measured yet Estimated
Mistral 7B v0.3
mistral:7b
Fits 7.8 20 to 38 Fast not measured yet Estimated
Llama 3.1 8B
llama3.1:8b
Fits 8.3 18 to 34 Fast not measured yet Estimated
Qwen3 8B
qwen3:8b · thinks first
Fits 8.9 17 to 32 Fast not measured yet Estimated
Gemma 3 12B
gemma3:12b
Fits 15.9 11 to 21 Fast not measured yet Estimated
DeepSeek-R1 Distill Qwen 14B
deepseek-r1:14b · thinks first
Fits 13.7 10 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Phi-4 14B
phi4:14b
Fits 13.9 9.8 to 18 Unclear could be Moderate or Fast not measured yet Estimated
Qwen3 14B
qwen3:14b · thinks first
Fits 13.4 9.6 to 18 Unclear could be Moderate or Fast not measured yet Estimated
gpt-oss 20B
gpt-oss:20b · thinks first
Fits 16.5 22 to 41 Fast not measured yet Estimated
Gemma 3 27B
gemma3:27b
Fits 27.2 5.3 to 9.8 Moderate not measured yet Estimated
Qwen3 30B (A3B)
qwen3:30b · thinks first
Fits 22.6 26 to 49 Fast 9.3/10 Estimated
Qwen3 32B
qwen3:32b · thinks first
Fits 26.3 4.5 to 8.3 Unclear could be Slow or Moderate not measured yet Estimated
Llama 3.1 70B
llama3.1:70b
Fits 51.5 2.1 to 3.9 Slow not measured yet Estimated
gpt-oss 120B
gpt-oss:120b · thinks first
Fits 70.5 19 to 35 Fast not measured yet Estimated

Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.

Reported by others

Other people ran the standard llama-bench test on this chip and published the results. They are not Hardwarerig scores. The test uses a small 7-billion-parameter model, so larger models will be slower than these figures. All published benchmarks.

SetupModel and sizeWriting speed (tokens per second)Reading speed (tokens per second)Source
ROCm (HIP) Llama 2 7B, Q4_0 50.0 911 llama.cpp discussion 15021
read 2026-10-10
ROCm (HIP) Llama 2 7B, Q4_0 49.9 1004 llama.cpp discussion 15021
read 2026-10-10

Reported by others, not tested by us. Results come from a public community thread; builds and settings differ between submitters.

Published chip scores

Blender Open Data publishes the median render score of its Cycles test for each chip, and PassMark publishes average CPU and 3D scores, both from results people submitted. Higher is faster. These are not Hardwarerig scores. Scores from different tests, and from different Blender versions, are not comparable with each other.

ChipTestScoreSource
AMD Ryzen AI Max+ 395Blender render, processor, Blender 5.2.0391Blender Open Data
read 2026-10-22
AMD Ryzen AI Max+ 395PassMark CPU Mark (all cores)54826PassMark
read 2026-10-22
AMD Ryzen AI Max+ 395PassMark single-thread rating4144PassMark
read 2026-10-22

Editing, gaming, CAD and other work

Each app below publishes a minimum and a recommended system requirement. We compare them with this laptop's memory and graphics memory. We do not judge the graphics chip's class, the processor generation or the operating system, because the makers describe those in words: check the source link for the exact card, processor and system they name. Many apps and games run only on Windows or only on macOS. Integrated graphics count as below any requirement for a dedicated card. Not known means the maker does not state this laptop's graphics memory.

App32 GB64 GB128 GB
Video editing
Adobe Premiere ProRecommendedRecommendedRecommended
Adobe After EffectsBelow minimumBelow minimumBelow minimum
Final Cut ProRecommendedRecommendedRecommended
OBS StudioMinimumMinimumMinimum
Adobe Premiere ElementsRecommendedRecommendedRecommended
DaVinci ResolveMinimumMinimumMinimum
Photo editing and design
Adobe PhotoshopRecommendedRecommendedRecommended
Adobe Lightroom ClassicRecommendedRecommendedRecommended
Adobe IllustratorRecommendedRecommendedRecommended
AffinityRecommendedRecommendedRecommended
Adobe InDesignRecommendedRecommendedRecommended
Capture OneMinimumMinimumMinimum
KritaRecommendedRecommendedRecommended
Clip Studio PaintRecommendedRecommendedRecommended
3D, CAD and rendering
BlenderRecommendedRecommendedRecommended
Autodesk AutoCADMinimumMinimumMinimum
SOLIDWORKSRecommendedRecommendedRecommended
Autodesk FusionRecommendedRecommendedRecommended
Autodesk RevitMinimumMinimumMinimum
SketchUpBelow minimumBelow minimumBelow minimum
Autodesk MayaRecommendedRecommendedRecommended
Maxon Cinema 4DRecommendedRecommendedRecommended
RhinoRecommendedRecommendedRecommended
KeyShot StudioRecommendedRecommendedRecommended
Unreal Engine 5 editorRecommendedRecommendedRecommended
Unity editorMinimumMinimumMinimum
HoudiniRecommendedRecommendedRecommended
ZBrushRecommendedRecommendedRecommended
Adobe Substance 3D PainterBelow minimumBelow minimumBelow minimum
Autodesk 3ds MaxRecommendedRecommendedRecommended
Autodesk InventorMinimumMinimumMinimum
Autodesk Civil 3DMinimumMinimumMinimum
ArchicadRecommendedRecommendedRecommended
TwinmotionBelow minimumBelow minimumBelow minimum
Lumion ProBelow minimumBelow minimumBelow minimum
D5 RenderRecommendedRecommendedRecommended
Godot EngineMinimumMinimumMinimum
Gaming
Cyberpunk 2077Below minimumBelow minimumBelow minimum
Baldur's Gate 3Below minimumBelow minimumBelow minimum
Elden RingBelow minimumBelow minimumBelow minimum
Black Myth: WukongBelow minimumBelow minimumBelow minimum
StarfieldBelow minimumBelow minimumBelow minimum
Hogwarts LegacyBelow minimumBelow minimumBelow minimum
Counter-Strike 2MinimumMinimumMinimum
FortniteMinimumMinimumMinimum
Call of Duty: WarzoneBelow minimumBelow minimumBelow minimum
Microsoft Flight Simulator 2024Below minimumBelow minimumBelow minimum
Alan Wake 2Below minimumBelow minimumBelow minimum
Forza Horizon 5Below minimumBelow minimumBelow minimum
Red Dead Redemption 2Below minimumBelow minimumBelow minimum
Grand Theft Auto VBelow minimumBelow minimumBelow minimum
Marvel RivalsBelow minimumBelow minimumBelow minimum
Helldivers 2Below minimumBelow minimumBelow minimum
Hades IIMinimumMinimumMinimum
Stardew ValleyMinimumMinimumMinimum
Minecraft Java EditionMinimumMinimumMinimum
Apex LegendsMinimumMinimumMinimum
Rocket LeagueMinimumMinimumMinimum
Dota 2MinimumMinimumMinimum
Overwatch 2Below minimumBelow minimumBelow minimum
PalworldBelow minimumBelow minimumBelow minimum
Diablo IVBelow minimumBelow minimumBelow minimum
Path of Exile 2Below minimumBelow minimumBelow minimum
Monster Hunter WildsBelow minimumBelow minimumBelow minimum
Assassin's Creed ShadowsBelow minimumBelow minimumBelow minimum
Warhammer 40,000: Space Marine 2Below minimumBelow minimumBelow minimum
Silent Hill 2Below minimumBelow minimumBelow minimum
God of War RagnarokBelow minimumBelow minimumBelow minimum
The Witcher 3: Wild HuntBelow minimumBelow minimumBelow minimum
Sid Meier's Civilization VIIBelow minimumBelow minimumBelow minimum
Total War: Warhammer IIIRecommendedRecommendedRecommended
Cities: Skylines IIBelow minimumBelow minimumBelow minimum
F1 25Below minimumBelow minimumBelow minimum
EA Sports FC 25Below minimumBelow minimumBelow minimum
Forza MotorsportBelow minimumBelow minimumBelow minimum
Lethal CompanyBelow minimumBelow minimumBelow minimum
BalatroMinimumMinimumMinimum
Vampire SurvivorsMinimumMinimumMinimum
Hollow Knight: SilksongMinimumMinimumMinimum
SatisfactoryBelow minimumBelow minimumBelow minimum
RobloxMinimumMinimumMinimum
Genshin ImpactMinimumMinimumMinimum
AI image and video generation
InvokeAI with SD 1.5 modelsBelow minimumBelow minimumBelow minimum
InvokeAI with SDXL modelsBelow minimumBelow minimumBelow minimum
InvokeAI with FLUX.1 modelsBelow minimumBelow minimumBelow minimum
FooocusMinimumMinimumMinimum
LM StudioBelow minimumBelow minimumBelow minimum
JanRecommendedRecommendedRecommended
Music and audio production
Ableton Live 12MinimumMinimumMinimum
FL StudioMinimumMinimumMinimum
Logic ProMinimumMinimumMinimum
Pro ToolsMinimumMinimumMinimum
Steinberg CubaseMinimumMinimumMinimum
Native Instruments Kontakt 8RecommendedRecommendedRecommended
Bitwig StudioMinimumMinimumMinimum
Fender Studio ProMinimumMinimumMinimum
ReasonMinimumMinimumMinimum
Traktor Pro 4MinimumMinimumMinimum
Adobe AuditionRecommendedRecommendedRecommended
Software development
Android StudioRecommendedRecommendedRecommended
Visual Studio 2026RecommendedRecommendedRecommended
Docker DesktopMinimumMinimumMinimum
IntelliJ IDEAMinimumMinimumMinimum
Visual Studio CodeRecommendedRecommendedRecommended
VMware Workstation ProRecommendedRecommendedRecommended
Parallels DesktopRecommendedRecommendedRecommended
Everyday work
Microsoft 365MinimumMinimumMinimum
Zoom WorkplaceRecommendedRecommendedRecommended
Microsoft TeamsMinimumMinimumMinimum
Google ChromeMinimumMinimumMinimum
Windows 11MinimumMinimumMinimum

Labels follow the makers' published lists. All use cases.

Speed is the speed of writing an answer, shown as a range. Reading speed is not estimated. How the estimates work · How close they are · Back to the finder